Search

Vision Large Language Models (VLLMs) are transforming the intersection of computer vision and natural language processing. Nonetheless, the potential of using visual prompts for emotion recognition in these models remains largely unexplored and untapped. Traditional methods in VLLMs struggle with spatial localization and often discard valuable global context. To address this problem, we propose a Set-of-Vision prompting (SoV) approach that enhances zero-shot emotion recognition by using spatial information, such as bounding boxes and facial landmarks, to mark targets precisely. SoV improves accuracy in face count and emotion categorization while preserving the enriched image context. Through a battery of experimentation and analysis of recent commercial or open-source VLLMs, we evaluate the SoV model's ability to comprehend facial expressions in natural environments. Our findings demonstrate the effectiveness of integrating spatial visual prompts into VLLMs for improving emotion recognition performance., Comment: Accepted by EMNLP2024 (Main, Long paper)

Contrastive Language-Image Pre-training (CLIP) models have shown significant potential, particularly in zero-shot classification across diverse distribution shifts. Building on existing evaluations of overall classification robustness, this work aims to provide a more comprehensive assessment of CLIP by introducing several new perspectives. First, we investigate their robustness to variations in specific visual factors. Second, we assess two critical safety objectives--confidence uncertainty and out-of-distribution detection--beyond mere classification accuracy. Third, we evaluate the finesse with which CLIP models bridge the image and text modalities. Fourth, we extend our examination to 3D awareness in CLIP models, moving beyond traditional 2D image understanding. Finally, we explore the interaction between vision and language encoders within modern large multimodal models (LMMs) that utilize CLIP as the visual backbone, focusing on how this interaction impacts classification robustness. In each aspect, we consider the impact of six factors on CLIP models: model architecture, training distribution, training set size, fine-tuning, contrastive loss, and test-time prompts. Our study uncovers several previously unknown insights into CLIP. For instance, the architecture of the visual encoder in CLIP plays a significant role in their robustness against 3D corruption. CLIP models tend to exhibit a bias towards shape when making predictions. Moreover, this bias tends to diminish after fine-tuning on ImageNet. Vision-language models like LLaVA, leveraging the CLIP vision encoder, could exhibit benefits in classification performance for challenging categories over CLIP alone. Our findings are poised to offer valuable guidance for enhancing the robustness and reliability of CLIP models., Comment: 17 pages, 10 figures, extension of NeurIPS'23 work: A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP). arXiv admin note: text overlap with arXiv:2402.07410

In computer vision tasks, features often come from diverse representations, domains, and modalities, such as text, images, and videos. Effectively fusing these features is essential for robust performance, especially with the availability of powerful pre-trained models like vision-language models. However, common fusion methods, such as concatenation, element-wise operations, and non-linear techniques, often fail to capture structural relationships, deep feature interactions, and suffer from inefficiency or misalignment of features across domains. In this paper, we shift from high-dimensional feature space to a lower-dimensional, interpretable graph space by constructing similarity graphs that encode feature relationships at different levels, e.g., clip, frame, patch, token, etc. To capture deeper interactions, we use graph power expansions and introduce a learnable graph fusion operator to combine these graph powers for more effective fusion. Our approach is relationship-centric, operates in a homogeneous space, and is mathematically principled, resembling element-wise similarity score aggregation via multilinear polynomials. We demonstrate the effectiveness of our graph-based fusion method on video anomaly detection, showing strong performance across multi-representational, multi-modal, and multi-domain feature fusion tasks., Comment: Research paper

Accurately detecting and tracking high-speed, small objects, such as balls in sports videos, is challenging due to factors like motion blur and occlusion. Although recent deep learning frameworks like TrackNetV1, V2, and V3 have advanced tennis ball and shuttlecock tracking, they often struggle in scenarios with partial occlusion or low visibility. This is primarily because these models rely heavily on visual features without explicitly incorporating motion information, which is crucial for precise tracking and trajectory prediction. In this paper, we introduce an enhancement to the TrackNet family by fusing high-level visual features with learnable motion attention maps through a motion-aware fusion mechanism, effectively emphasizing the moving ball's location and improving tracking performance. Our approach leverages frame differencing maps, modulated by a motion prompt layer, to highlight key motion regions over time. Experimental results on the tennis ball and shuttlecock datasets show that our method enhances the tracking performance of both TrackNetV2 and V3. We refer to our lightweight, plug-and-play solution, built on top of the existing TrackNet, as TrackNetV4., Comment: Research report

Anxiety is a common mental health condition characterised by excessive worry, fear and apprehension about everyday situations. Even with significant progress over the past few years, predicting anxiety from electroencephalographic (EEG) signals, specifically using error-related negativity (ERN), still remains challenging. Following the PRISMA protocol, this paper systematically reviews 54 research papers on using EEG and ERN markers for anxiety detection published in the last 10 years (2013 -- 2023). Our analysis highlights the wide usage of traditional machine learning, such as support vector machines and random forests, as well as deep learning models, such as convolutional neural networks and recurrent neural networks across different data types. Our analysis reveals that the development of a robust and generic anxiety prediction method still needs to address real-world challenges, such as task-specific setup, feature selection and computational modelling. We conclude this review by offering potential future direction for non-invasive, objective anxiety diagnostics, deployed across diverse populations and anxiety sub-types.

With the rapid advancements in multimodal generative technology, Affective Computing research has provoked discussion about the potential consequences of AI systems equipped with emotional intelligence. Affective Computing involves the design, evaluation, and implementation of Emotion AI and related technologies aimed at improving people's lives. Designing a computational model in affective computing requires vast amounts of multimodal data, including RGB images, video, audio, text, and physiological signals. Moreover, Affective Computing research is deeply engaged with ethical considerations at various stages-from training emotionally intelligent models on large-scale human data to deploying these models in specific applications. Fundamentally, the development of any AI system must prioritize its impact on humans, aiming to augment and enhance human abilities rather than replace them, while drawing inspiration from human intelligence in a safe and responsible manner. The MRAC 2024 Track 1 workshop seeks to extend these principles from controlled, small-scale lab environments to real-world, large-scale contexts, emphasizing responsible development. The workshop also aims to highlight the potential implications of generative technology, along with the ethical consequences of its use, to researchers and industry professionals. To the best of our knowledge, this is the first workshop series to comprehensively address the full spectrum of multimodal, generative affective computing from a responsible AI perspective, and this is the second iteration of this workshop. Webpage: https://react-ws.github.io/2024/, Comment: ACM MM Workshop 2024. Workshop webpage: https://react-ws.github.io/2024/

Estimating the Most Important Person (MIP) in any social event setup is a challenging problem mainly due to contextual complexity and scarcity of labeled data. Moreover, the causality aspects of MIP estimation are quite subjective and diverse. To this end, we aim to address the problem by annotating a large-scale `in-the-wild' dataset for identifying human perceptions about the `Most Important Person (MIP)' in an image. The paper provides a thorough description of our proposed Multimodal Large Language Model (MLLM) based data annotation strategy, and a thorough data quality analysis. Further, we perform a comprehensive benchmarking of the proposed dataset utilizing state-of-the-art MIP localization methods, indicating a significant drop in performance compared to existing datasets. The performance drop shows that the existing MIP localization algorithms must be more robust with respect to `in-the-wild' situations. We believe the proposed dataset will play a vital role in building the next-generation social situation understanding methods. The code and data is available at https://github.com/surbhimadan92/MIP-GAF., Comment: Accepted for publication at WACV 2025

In response to the global need for efficient early diagnosis of Autism Spectrum Disorder (ASD), this paper bridges the gap between traditional, time-consuming diagnostic methods and potential automated solutions. We propose a multi-atlas deep ensemble network, MADE-for-ASD, that integrates multiple atlases of the brain's functional magnetic resonance imaging (fMRI) data through a weighted deep ensemble network. Our approach integrates demographic information into the prediction workflow, which enhances ASD diagnosis performance and offers a more holistic perspective on patient profiling. We experiment with the well-known publicly available ABIDE (Autism Brain Imaging Data Exchange) I dataset, consisting of resting state fMRI data from 17 different laboratories around the globe. Our proposed system achieves 75.20% accuracy on the entire dataset and 96.40% on a specific subset $-$ both surpassing reported ASD diagnosis accuracy in ABIDE I fMRI studies. Specifically, our model improves by 4.4 percentage points over prior works on the same amount of data. The model exhibits a sensitivity of 82.90% and a specificity of 69.70% on the entire dataset, and 91.00% and 99.50%, respectively, on the specific subset. We leverage the F-score to pinpoint the top 10 ROI in ASD diagnosis, such as precuneus and anterior cingulate/ventromedial. The proposed system can potentially pave the way for more cost-effective, efficient and scalable strategies in ASD diagnosis. Codes and evaluations are publicly available at https://github.com/hasan-rakibul/MADE-for-ASD., Comment: Xuehan Liu and Md Rakibul Hasan contributed equally to this work

Videos contain rich spatio-temporal information. Traditional methods for extracting motion, used in tasks such as action recognition, often rely on visual contents rather than precise motion features. This phenomenon is referred to as 'blind motion extraction' behavior, which proves inefficient in capturing motions of interest due to a lack of motion-guided cues. Recently, attention mechanisms have enhanced many computer vision tasks by effectively highlighting salient visual areas. Inspired by this, we propose a modified Sigmoid function with learnable slope and shift parameters as an attention mechanism to modulate motion signals from frame differencing maps. This approach generates a sequence of attention maps that enhance the processing of motion-related video content. To ensure temporal continuity and smoothness of the attention maps, we apply pair-wise temporal attention variation regularization to remove unwanted motions (e.g., noise) while preserving important ones. We then perform Hadamard product between each pair of attention maps and the original video frames to highlight the evolving motions of interest over time. These highlighted motions, termed video motion prompts, are subsequently used as inputs to the model instead of the original video frames. We formalize this process as a motion prompt layer and incorporate the regularization term into the loss function to learn better motion prompts. This layer serves as an adapter between the model and the video data, bridging the gap between traditional 'blind motion extraction' and the extraction of relevant motions of interest. We show that our lightweight, plug-and-play motion prompt layer seamlessly integrates into models like SlowFast, X3D, and TimeSformer, enhancing performance on benchmarks such as FineGym and MPII Cooking 2., Comment: Accepted at the 16th Asian Conference on Machine Learning (ACML 2024)

This work aims to develop a measure that can accurately rank the performance of various classifiers when they are tested on unlabeled data from out-of-distribution (OOD) distributions. We commence by demonstrating that conventional uncertainty metrics, notably the maximum Softmax prediction probability, possess inherent utility in forecasting model generalization across certain OOD contexts. Building on this insight, we introduce a new measure called Softmax Correlation (SoftmaxCorr). It calculates the cosine similarity between a class-class correlation matrix, constructed from Softmax output vectors across an unlabeled test dataset, and a predefined reference matrix that embodies ideal class correlations. A high resemblance of predictions to the reference matrix signals that the model delivers confident and uniform predictions across all categories, reflecting minimal uncertainty and confusion. Through rigorous evaluation across a suite of datasets, including ImageNet, CIFAR-10, and WILDS, we affirm the predictive validity of SoftmaxCorr in accurately forecasting model performance within both in-distribution (ID) and OOD settings. Furthermore, we discuss the limitations of our proposed measure and suggest avenues for future research., Comment: TMLR 2024 (https://openreview.net/forum?id=vtiDUgGjyx)

Objective: Heart murmurs are abnormal sounds caused by turbulent blood flow within the heart. Several diagnostic methods are available to detect heart murmurs and their severity, such as cardiac auscultation, echocardiography, phonocardiogram (PCG), etc. However, these methods have limitations, including extensive training and experience among healthcare providers, cost and accessibility of echocardiography, as well as noise interference and PCG data processing. This study aims to develop a novel end-to-end real-time heart murmur detection approach using traditional and depthwise separable convolutional networks. Methods: Continuous wavelet transform (CWT) was applied to extract meaningful features from the PCG data. The proposed network has three parts: the Squeeze net, the Bottleneck, and the Expansion net. The Squeeze net generates a compressed data representation, whereas the Bottleneck layer reduces computational complexity using a depthwise-separable convolutional network. The Expansion net is responsible for up-sampling the compressed data to a higher dimension, capturing tiny details of the representative data. Results: For evaluation, we used four publicly available datasets and achieved state-of-the-art performance in all datasets. Furthermore, we tested our proposed network on two resource-constrained devices: a Raspberry PI and an Android device, stripping it down into a tiny machine learning model (TinyML), achieving a maximum of 99.70%. Conclusion: The proposed model offers a deep learning framework for real-time accurate heart murmur detection within limited resources. Significance: It will significantly result in more accessible and practical medical services and reduced diagnosis time to assist medical professionals. The code is publicly available at TBA., Comment: 8-page main paper and 4-page supplementary material

In this paper, we present a novel benchmark for Emotion Recognition using facial landmarks extracted from realistic news videos. Traditional methods relying on RGB images are resource-intensive, whereas our approach with Facial Landmark Emotion Recognition (FLER) offers a simplified yet effective alternative. By leveraging Graph Neural Networks (GNNs) to analyze the geometric and spatial relationships of facial landmarks, our method enhances the understanding and accuracy of emotion recognition. We discuss the advancements and challenges in deep learning techniques for emotion recognition, particularly focusing on Graph Neural Networks (GNNs) and Transformers. Our experimental results demonstrate the viability and potential of our dataset as a benchmark, setting a new direction for future research in emotion recognition technologies. The codes and models are at: https://github.com/wangzhifengharrison/benchmark_real_news

Diabetes, resulting from inadequate insulin production or utilization, causes extensive harm to the body. Existing diagnostic methods are often invasive and come with drawbacks, such as cost constraints. Although there are machine learning models like Classwise k Nearest Neighbor (CkNN) and General Regression Neural Network (GRNN), they struggle with imbalanced data and result in under-performance. Leveraging advancements in sensor technology and machine learning, we propose a non-invasive diabetes diagnosis using a Back Propagation Neural Network (BPNN) with batch normalization, incorporating data re-sampling and normalization for class balancing. Our method addresses existing challenges such as limited performance associated with traditional machine learning. Experimental results on three datasets show significant improvements in overall accuracy, sensitivity, and specificity compared to traditional methods. Notably, we achieve accuracies of 89.81% in Pima diabetes dataset, 75.49% in CDC BRFSS2015 dataset, and 95.28% in Mesra Diabetes dataset. This underscores the potential of deep learning models for robust diabetes diagnosis. See project website https://steve-zeyu-zhang.github.io/DiabetesDiagnosis/, Comment: Accepted to ACIIDS 2024

Vision-Language Models (VLMs) have emerged as the dominant approach for zero-shot recognition, adept at handling diverse scenarios and significant distribution changes. However, their deployment in risk-sensitive areas requires a deeper understanding of their uncertainty estimation capabilities, a relatively uncharted area. In this study, we explore the calibration properties of VLMs across different architectures, datasets, and training strategies. In particular, we analyze the uncertainty estimation performance of VLMs when calibrated in one domain, label set or hierarchy level, and tested in a different one. Our findings reveal that while VLMs are not inherently calibrated for uncertainty, temperature scaling significantly and consistently improves calibration, even across shifts in distribution and changes in label set. Moreover, VLMs can be calibrated with a very small set of examples. Through detailed experimentation, we highlight the potential applications and importance of our insights, aiming for more reliable and effective use of VLMs in critical, real-world scenarios., Comment: ICML 2024 Camera Ready

Contrastive Language-Image Pre-training (CLIP) models have demonstrated remarkable generalization capabilities across multiple challenging distribution shifts. However, there is still much to be explored in terms of their robustness to the variations of specific visual factors. In real-world applications, reliable and safe systems must consider other safety objectives beyond classification accuracy, such as predictive uncertainty. Yet, the effectiveness of CLIP models on such safety-related features is less-explored. Driven by the above, this work comprehensively investigates the safety objectives of CLIP models, specifically focusing on three key properties: resilience to visual factor variations, calibrated uncertainty estimations, and the ability to detect anomalous inputs. To this end, we study 83 CLIP models and 127 ImageNet classifiers. They are diverse in architecture, (pre)training distribution and training strategies. We consider 10 visual factors (e.g., shape and pattern), 5 types of out-of-distribution data, and 8 natural and challenging test conditions with different shift types, such as texture, style, and perturbation shifts. Our study has unveiled several previously unknown insights into CLIP models. For instance, they are not consistently more calibrated than other ImageNet models, which contradicts existing findings. Additionally, our analysis underscores the significance of training source design by showcasing its profound influence on the three safety-related properties. We believe our comprehensive study can shed light on and help guide the development of more robust and reliable CLIP models., Comment: Accepted by NeurIPS 2023

Video Anomaly Detection (VAD) finds widespread applications in security surveillance, traffic monitoring, industrial monitoring, and healthcare. Despite extensive research efforts, there remains a lack of concise reviews that provide insightful guidance for researchers. Such reviews would serve as quick references to grasp current challenges, research trends, and future directions. In this paper, we present such a review, examining models and datasets from various perspectives. We emphasize the critical relationship between model and dataset, where the quality and diversity of datasets profoundly influence model performance, and dataset development adapts to the evolving needs of emerging approaches. Our review identifies practical issues, including the absence of comprehensive datasets with diverse scenarios. To address this, we introduce a new dataset, Multi-Scenario Anomaly Detection (MSAD), comprising 14 distinct scenarios captured from various camera views. Our dataset has diverse motion patterns and challenging variations, such as different lighting and weather conditions, providing a robust foundation for training superior models. We conduct an in-depth analysis of recent representative models using MSAD and highlight its potential in addressing the challenges of detecting anomalies across diverse and evolving surveillance scenarios. Our dataset is available here., Comment: Research report

Effectively extracting motions from video is a critical and long-standing problem for action recognition. This problem is very challenging because motions (i) do not have an explicit form, (ii) have various concepts such as displacement, velocity, and acceleration, and (iii) often contain noise caused by unstable pixels. Addressing these challenges, we propose the Taylor video, a new video format that highlights the dominate motions (e.g., a waving hand) in each of its frames named the Taylor frame. Taylor video is named after Taylor series, which approximates a function at a given point using important terms. In the scenario of videos, we define an implicit motion-extraction function which aims to extract motions from video temporal block. In this block, using the frames, the difference frames, and higher-order difference frames, we perform Taylor expansion to approximate this function at the starting frame. We show the summation of the higher-order terms in the Taylor series gives us dominant motion patterns, where static objects, small and unstable motions are removed. Experimentally we show that Taylor videos are effective inputs to popular architectures including 2D CNNs, 3D CNNs, and transformers. When used individually, Taylor videos yield competitive action recognition accuracy compared to RGB videos and optical flow. When fused with RGB or optical flow videos, further accuracy improvement is achieved. Additionally, we apply Taylor video computation to human skeleton sequences, resulting in Taylor skeleton sequences that outperform the use of original skeletons for skeleton-based action recognition., Comment: Published at the International Conference on Machine Learning (ICML 2024)

Jointly considering multiple camera views (multi-view) is very effective for pedestrian detection under occlusion. For such multi-view systems, it is critical to have well-designed camera configurations, including camera locations, directions, and fields-of-view (FoVs). Usually, these configurations are crafted based on human experience or heuristics. In this work, we present a novel solution that features a transformer-based camera configuration generator. Using reinforcement learning, this generator autonomously explores vast combinations within the action space and searches for configurations that give the highest detection accuracy according to the training dataset. The generator learns advanced techniques like maximizing coverage, minimizing occlusion, and promoting collaboration. Across multiple simulation scenarios, the configurations generated by our transformer-based model consistently outperform random search, heuristic-based methods, and configurations designed by human experts, shedding light on future camera layout optimization.

The detection and localization of highly realistic deepfake audio-visual content are challenging even for the most advanced state-of-the-art methods. While most of the research efforts in this domain are focused on detecting high-quality deepfake images and videos, only a few works address the problem of the localization of small segments of audio-visual manipulations embedded in real videos. In this research, we emulate the process of such content generation and propose the AV-Deepfake1M dataset. The dataset contains content-driven (i) video manipulations, (ii) audio manipulations, and (iii) audio-visual manipulations for more than 2K subjects resulting in a total of more than 1M videos. The paper provides a thorough description of the proposed data generation pipeline accompanied by a rigorous analysis of the quality of the generated data. The comprehensive benchmark of the proposed dataset utilizing state-of-the-art deepfake detection and localization methods indicates a significant drop in performance compared to previous datasets. The proposed dataset will play a vital role in building the next-generation deepfake localization methods. The dataset and associated code are available at https://github.com/ControlNet/AV-Deepfake1M ., Comment: Accepted by ACM MM 2024

Empathy indicates an individual's ability to understand others. Over the past few years, empathy has drawn attention from various disciplines, including but not limited to Affective Computing, Cognitive Science and Psychology. Detecting empathy has potential applications in society, healthcare and education. Despite being a broad and overlapping topic, the avenue of empathy detection leveraging Machine Learning remains underexplored from a systematic literature review perspective. We collected 828 papers from 10 well-known databases, systematically screened them and analysed the final 61 papers. Our analyses reveal several prominent task formulations $-$ including empathy on localised utterances or overall expressions, unidirectional or parallel empathy, and emotional contagion $-$ in monadic, dyadic and group interactions. Empathy detection methods are summarised based on four input modalities $-$ text, audiovisual, audio and physiological signals $-$ thereby presenting modality-specific network architecture design protocols. We discuss challenges, research gaps and potential applications in the Affective Computing-based empathy domain, which can facilitate new avenues of exploration. We further enlist the public availability of datasets and codes. We believe that our work is a stepping stone to developing a robust empathy detection system that can be deployed in practice to enhance the overall well-being of human life., Comment: This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice

In contrastive learning, two views of an original image, generated by different augmentations, are considered a positive pair, and their similarity is required to be high. Similarly, two views of distinct images form a negative pair, with encouraged low similarity. Typically, a single similarity measure, provided by a lone projection head, evaluates positive and negative sample pairs. However, due to diverse augmentation strategies and varying intra-sample similarity, views from the same image may not always be similar. Additionally, owing to inter-sample similarity, views from different images may be more akin than those from the same image. Consequently, enforcing high similarity for positive pairs and low similarity for negative pairs may be unattainable, and in some cases, such enforcement could detrimentally impact performance. To address this challenge, we propose using multiple projection heads, each producing a distinct set of features. Our pre-training loss function emerges from a solution to the maximum likelihood estimation over head-wise posterior distributions of positive samples given observations. This loss incorporates the similarity measure over positive and negative pairs, each re-weighted by an individual adaptive temperature, regulated to prevent ill solutions. Our approach, Adaptive Multi-Head Contrastive Learning (AMCL), can be applied to and experimentally enhances several popular contrastive learning methods such as SimCLR, MoCo, and Barlow Twins. The improvement remains consistent across various backbones and linear probing epochs, and becomes more significant when employing multiple augmentation methods., Comment: Accepted at the 18th European Conference on Computer Vision (ECCV 2024)

Automating the checkout process is important in smart retail, where users effortlessly pass products by hand through a camera, triggering automatic product detection, tracking, and counting. In this emerging area, due to the lack of annotated training data, we introduce a dataset comprised of product 3D models, which allows for fast, flexible, and large-scale training data generation through graphic engine rendering. Within this context, we discern an intriguing facet, because of the user "hands-on" approach, bias in user behavior leads to distinct patterns in the real checkout process. The existence of such patterns would compromise training effectiveness if training data fail to reflect the same. To address this user bias problem, we propose a training data optimization framework, i.e., training with digital twins (DtTrain). Specifically, we leverage the product 3D models and optimize their rendering viewpoint and illumination to generate "digital twins" that visually resemble representative user images. These digital twins, inherit product labels and, when augmented, form the Digital Twin training set (DT set). Because the digital twins individually mimic user bias, the resulting DT training set better reflects the characteristics of the target scenario and allows us to train more effective product detection and tracking models. In our experiment, we show that DT set outperforms training sets created by existing dataset synthesis methods in terms of counting accuracy. Moreover, by combining DT set with pseudo-labeled real checkout data, further improvement is observed. The code is available at https://github.com/yorkeyao/Automated-Retail-Checkout.

This paper proposes a feedback mechanism to change behavioural patterns using the Pavlok device. Pavlok utilises beeps, vibration and shocks as a mode of aversion technique to help individuals with behaviour modification. While the device can be useful in certain periodic daily life situations, like alarms and exercise notifications, the device relies on manual operations that limit its usage. To automate behaviour modification, we propose a framework that first detects targeted behaviours through a lightweight deep learning model and subsequently nudges the user through Pavlok. Our proposed solution is implemented and verified in the context of snoring, which captures audio from the environment following a prediction of whether the audio content is a snore or not using a 1D convolutional neural network. Based on the prediction, we use Pavlok to nudge users for preventive measures, such as a change in sleeping posture. We believe that this simple solution can help people to change their atomic habits, which may lead to long-term health benefits. Our proposed real-time, lightweight model (99.8% less parameters over SOTA; 1,278,049 --> 1337) achieves SOTA performance (test accuracy of 0.99) on a public domain benchmark. The code and model are publicly available at https://github.com/hasan-rakibul/pavlok-nudge-snore., Comment: Md Rakibul Hasan and Shreya Ghosh are co-first authors

Automatic group emotion recognition plays an important role in understanding complex human-human interaction. This paper introduces, Emolysis, a Python-based, standalone open-source group emotion analysis toolkit for use in different social situations upon getting consent from the users. Given any input video, Emolysis processes synchronized multimodal input and maps it to group level emotion, valence and arousal. Additionally, the toolkit supports major mobile and desktop platforms (Android, iOS, Windows). The Emolysis platform also comes with an intuitive graphical user interface that allows users to select different modalities and target persons for more fine-grained emotion analysis. Emolysis is freely available for academic research and encourages application developers to extend it to application specific environments on top of the existing system. We believe that the extension mechanism is quite straightforward. Our code models and interface are available at https://github.com/ControlNet/emolysis., Comment: Accepted by ACII Demo 2024. Both Shreya Ghosh and Zhixi Cai contributed equally to this research

Most deepfake detection methods focus on detecting spatial and/or spatio-temporal changes in facial attributes and are centered around the binary classification task of detecting whether a video is real or fake. This is because available benchmark datasets contain mostly visual-only modifications present in the entirety of the video. However, a sophisticated deepfake may include small segments of audio or audio-visual manipulations that can completely change the meaning of the video content. To addresses this gap, we propose and benchmark a new dataset, Localized Audio Visual DeepFake (LAV-DF), consisting of strategic content-driven audio, visual and audio-visual manipulations. The proposed baseline method, Boundary Aware Temporal Forgery Detection (BA-TFD), is a 3D Convolutional Neural Network-based architecture which effectively captures multimodal manipulations. We further improve (i.e. BA-TFD+) the baseline method by replacing the backbone with a Multiscale Vision Transformer and guide the training process with contrastive, frame classification, boundary matching and multimodal boundary matching loss functions. The quantitative analysis demonstrates the superiority of BA-TFD+ on temporal forgery localization and deepfake detection tasks using several benchmark datasets including our newly proposed dataset. The dataset, models and code are available at https://github.com/ControlNet/LAV-DF., Comment: The paper is under consideration/review at Computer Vision and Image Understanding Journal

We consider a scenario where we have access to the target domain, but cannot afford on-the-fly training data annotation, and instead would like to construct an alternative training set from a large-scale data pool such that a competitive model can be obtained. We propose a search and pruning (SnP) solution to this training data search problem, tailored to object re-identification (re-ID), an application aiming to match the same object captured by different cameras. Specifically, the search stage identifies and merges clusters of source identities which exhibit similar distributions with the target domain. The second stage, subject to a budget, then selects identities and their images from the Stage I output, to control the size of the resulting training set for efficient training. The two steps provide us with training sets 80\% smaller than the source pool while achieving a similar or even higher re-ID accuracy. These training sets are also shown to be superior to a few existing search methods such as random sampling and greedy sampling under the same budget on training data size. If we release the budget, training sets resulting from the first stage alone allow even higher re-ID accuracy. We provide interesting discussions on the specificity of our method to the re-ID problem and particularly its role in bridging the re-ID domain gap. The code is available at https://github.com/yorkeyao/SnP., Comment: Accepted to CVPR2023

This work investigates dataset vectorization for two dataset-level tasks: assessing training set suitability and test set difficulty. The former measures how suitable a training set is for a target domain, while the latter studies how challenging a test set is for a learned model. Central to the two tasks is measuring the underlying relationship between datasets. This needs a desirable dataset vectorization scheme, which should preserve as much discriminative dataset information as possible so that the distance between the resulting dataset vectors can reflect dataset-to-dataset similarity. To this end, we propose a bag-of-prototypes (BoP) dataset representation that extends the image-level bag consisting of patch descriptors to dataset-level bag consisting of semantic prototypes. Specifically, we develop a codebook consisting of K prototypes clustered from a reference dataset. Given a dataset to be encoded, we quantize each of its image features to a certain prototype in the codebook and obtain a K-dimensional histogram. Without assuming access to dataset labels, the BoP representation provides a rich characterization of the dataset semantic distribution. Furthermore, BoP representations cooperate well with Jensen-Shannon divergence for measuring dataset-to-dataset similarity. Although very simple, BoP consistently shows its advantage over existing representations on a series of benchmarks for two dataset-level tasks., Comment: CVPR 2023 camera-ready

Fine-tuning is widely applied in image classification tasks as a transfer learning approach. It re-uses the knowledge from a source task to learn and obtain a high performance in target tasks. Fine-tuning is able to alleviate the challenge of insufficient training data and expensive labelling of new data. However, standard fine-tuning has limited performance in complex data distributions. To address this issue, we propose the Adaptable Multi-tuning method, which adaptively determines each data sample's fine-tuning strategy. In this framework, multiple fine-tuning settings and one policy network are defined. The policy network in Adaptable Multi-tuning can dynamically adjust to an optimal weighting to feed different samples into models that are trained using different fine-tuning strategies. Our method outperforms the standard fine-tuning approach by 1.69%, 2.79% on the datasets FGVC-Aircraft, and Describable Texture, yielding comparable performance on the datasets Stanford Cars, CIFAR-10, and Fashion-MNIST., Comment: 9 pages

Skeleton sequences are compact and lightweight. Numerous skeleton-based action recognizers have been proposed to classify human behaviors. In this work, we aim to incorporate components that are compatible with existing models and further improve their accuracy. To this end, we design two temporal accessories: discrete cosine encoding (DCE) and chronological loss (CRL). DCE facilitates models to analyze motion patterns from the frequency domain and meanwhile alleviates the influence of signal noise. CRL guides networks to explicitly capture the sequence's chronological order. These two components consistently endow many recently-proposed action recognizers with accuracy boosts, achieving new state-of-the-art (SOTA) accuracy on two large datasets., Comment: ECCV2022-RWS

Deep neural networks such as convolutional neural networks (CNNs) and transformers have achieved many successes in image classification in recent years. It has been consistently demonstrated that best practice for image classification is when large deep models can be trained on abundant labelled data. However there are many real world scenarios where the requirement for large amounts of training data to get the best performance cannot be met. In these scenarios transfer learning can help improve performance. To date there have been no surveys that comprehensively review deep transfer learning as it relates to image classification overall. However, several recent general surveys of deep transfer learning and ones that relate to particular specialised target image classification tasks have been published. We believe it is important for the future progress in the field that all current knowledge is collated and the overarching patterns analysed and discussed. In this survey we formally define deep transfer learning and the problem it attempts to solve in relation to image classification. We survey the current state of the field and identify where recent progress has been made. We show where the gaps in current knowledge are and make suggestions for how to progress the field to fill in these knowledge gaps. We present a new taxonomy of the applications of transfer learning for image classification. This taxonomy makes it easier to see overarching patterns of where transfer learning has been effective and, where it has failed to fulfill its potential. This also allows us to suggest where the problems lie and how it could be used more effectively. We show that under this new taxonomy, many of the applications where transfer learning has been shown to be ineffective or even hinder performance are to be expected when taking into account the source and target datasets and the techniques used.

Skeleton-based action recognition, as a subarea of action recognition, is swiftly accumulating attention and popularity. The task is to recognize actions performed by human articulation points. Compared with other data modalities, 3D human skeleton representations have extensive unique desirable characteristics, including succinctness, robustness, racial-impartiality, and many more. We aim to provide a roadmap for new and existing researchers a on the landscapes of skeleton-based action recognition for new and existing researchers. To this end, we present a review in the form of a taxonomy on existing works of skeleton-based action recognition. We partition them into four major categories: (1) datasets; (2) extracting spatial features; (3) capturing temporal patterns; (4) improving signal quality. For each method, we provide concise yet informatively-sufficient descriptions. To promote more fair and comprehensive evaluation on existing approaches of skeleton-based action recognition, we collect ANUBIS, a large-scale human skeleton dataset. Compared with previously collected dataset, ANUBIS are advantageous in the following four aspects: (1) employing more recently released sensors; (2) containing novel back view; (3) encouraging high enthusiasm of subjects; (4) including actions of the COVID pandemic era. Using ANUBIS, we comparably benchmark performance of current skeleton-based action recognizers. At the end of this paper, we outlook future development of skeleton-based action recognition by listing several new technical problems. We believe they are valuable to solve in order to commercialize skeleton-based action recognition in the near future. The dataset of ANUBIS is available at: http://hcc-workshop.anu.edu.au/webs/anu101/home.

This article aims to use graphic engines to simulate a large number of training data that have free annotations and possibly strongly resemble to real-world data. Between synthetic and real, a two-level domain gap exists, involving content level and appearance level. While the latter is concerned with appearance style, the former problem arises from a different mechanism, i.e., content mismatch in attributes such as camera viewpoint, object placement and lighting conditions. In contrast to the widely-studied appearance-level gap, the content-level discrepancy has not been broadly studied. To address the content-level misalignment, we propose an attribute descent approach that automatically optimizes engine attributes to enable synthetic data to approximate real-world data. We verify our method on object-centric tasks, wherein an object takes up a major portion of an image. In these tasks, the search space is relatively small, and the optimization of each attribute yields sufficiently obvious supervision signals. We collect a new synthetic asset VehicleX, and reformat and reuse existing the synthetic assets ObjectX and PersonX. Extensive experiments on image classification and object re-identification confirm that adapted synthetic data can be effectively used in three scenarios: training with synthetic data only, training data augmentation and numerically understanding dataset content.

This paper does not contain technical novelty but introduces our key discoveries in a data generation protocol, a database and insights. We aim to address the lack of large-scale datasets in micro-expression (MiE) recognition due to the prohibitive cost of data collection, which renders large-scale training less feasible. To this end, we develop a protocol to automatically synthesize large scale MiE training data that allow us to train improved recognition models for real-world test data. Specifically, we discover three types of Action Units (AUs) that can constitute trainable MiEs. These AUs come from real-world MiEs, early frames of macro-expression videos, and the relationship between AUs and expression categories defined by human expert knowledge. With these AUs, our protocol then employs large numbers of face images of various identities and an off-the-shelf face generator for MiE synthesis, yielding the MiE-X dataset. MiE recognition models are trained or pre-trained on MiE-X and evaluated on real-world test sets, where very competitive accuracy is obtained. Experimental results not only validate the effectiveness of the discovered AUs and MiE-X dataset but also reveal some interesting properties of MiEs: they generalize across faces, are close to early-stage macro-expressions, and can be manually defined., Comment: European Conference on Computer Vision 2022

Discrete gene regulatory networks (GRNs) play a vital role in the study of robustness and modularity. A common method of evaluating the robustness of GRNs is to measure their ability to regulate a set of perturbed gene activation patterns back to their unperturbed forms. Usually, perturbations are obtained by collecting random samples produced by a predefined distribution of gene activation patterns. This sampling method introduces stochasticity, in turn inducing dynamicity. This dynamicity is imposed on top of an already complex fitness landscape. So where sampling is used, it is important to understand which effects arise from the structure of the fitness landscape, and which arise from the dynamicity imposed on it. Stochasticity of the fitness function also causes difficulties in reproducibility and in post-experimental analyses. We develop a deterministic distributional fitness evaluation by considering the complete distribution of gene activity patterns, so as to avoid stochasticity in fitness assessment. This fitness evaluation facilitates repeatability. Its determinism permits us to ascertain theoretical bounds on the fitness, and thus to identify whether the algorithm has reached a global optimum. It enables us to differentiate the effects of the problem domain from those of the noisy fitness evaluation, and thus to resolve two remaining anomalies in the behaviour of the problem domain of~\citet{espinosa2010specialization}. We also reveal some properties of solution GRNs that lead them to be robust and modular, leading to a deeper understanding of the nature of the problem domain. We conclude by discussing potential directions toward simulating and understanding the emergence of modularity in larger, more complex domains, which is key both to generating more useful modular solutions, and to understanding the ubiquity of modularity in biological systems., Comment: An paper accepted by the Artificial Life journal

Physical symptoms caused by high stress commonly happen in our daily lives, leading to the importance of stress recognition systems. This study aims to improve stress classification by selecting appropriate features from Thermal-stress data, ANUstressDB. We explored three different feature selection techniques: correlation analysis, magnitude measure, and genetic algorithm. Support Vector Machine (SVM) and Artificial Neural Network (ANN) models were involved in measuring these three algorithms. Our result indicates that the genetic algorithm combined with ANNs can improve the prediction accuracy by 19.1% compared to the baseline. Moreover, the magnitude measure performed best among the three feature selection algorithms regarding the balance of computation time and performance. These findings are likely to improve the accuracy of current stress recognition systems., Comment: 10 pages, 5 figurs, 8 tables, accepted by ACUR2021

Deep learning (DL) models are widely used to provide a more convenient and smarter life. However, biased algorithms will negatively influence us. For instance, groups targeted by biased algorithms will feel unfairly treated and even fearful of negative consequences of these biases. This work targets biased generative models' behaviors, identifying the cause of the biases and eliminating them. We can (as expected) conclude that biased data causes biased predictions of face frontalization models. Varying the proportions of male and female faces in the training data can have a substantial effect on behavior on the test data: we found that the seemingly obvious choice of 50:50 proportions was not the best for this dataset to reduce biased behavior on female faces, which was 71% unbiased as compared to our top unbiased rate of 84%. Failure in generation and generating incorrect gender faces are two behaviors of these models. In addition, only some layers in face frontalization models are vulnerable to biased datasets. Optimizing the skip-connections of the generator in face frontalization models can make models less biased. We conclude that it is likely to be impossible to eliminate all training bias without an unlimited size dataset, and our experiments show that the bias can be reduced and quantified. We believe the next best to a perfect unbiased predictor is one that has minimized the remaining known bias., Comment: 8 pages, 11 figures; accepted by IJCNN2021

The current standard for a variety of computer vision tasks using smaller numbers of labelled training examples is to fine-tune from weights pre-trained on a large image classification dataset such as ImageNet. The application of transfer learning and transfer learning methods tends to be rigidly binary. A model is either pre-trained or not pre-trained. Pre-training a model either increases performance or decreases it, the latter being defined as negative transfer. Application of L2-SP regularisation that decays the weights towards their pre-trained values is either applied or all weights are decayed towards 0. This paper re-examines these assumptions. Our recommendations are based on extensive empirical evaluation that demonstrate the application of a non-binary approach to achieve optimal results. (1) Achieving best performance on each individual dataset requires careful adjustment of various transfer learning hyperparameters not usually considered, including number of layers to transfer, different learning rates for different layers and different combinations of L2SP and L2 regularization. (2) Best practice can be achieved using a number of measures of how well the pre-trained weights fit the target dataset to guide optimal hyperparameters. We present methods for non-binary transfer learning including combining L2SP and L2 regularization and performing non-traditional fine-tuning hyperparameter searches. Finally we suggest heuristics for determining the optimal transfer learning hyperparameters. The benefits of using a non-binary approach are supported by final results that come close to or exceed state of the art performance on a variety of tasks that have traditionally been more difficult for transfer learning., Comment: 9 pages, 6 figures

Cross-entropy loss with softmax output is a standard choice to train neural network classifiers. We give a new view of neural network classifiers with softmax and cross-entropy as mutual information evaluators. We show that when the dataset is balanced, training a neural network with cross-entropy maximises the mutual information between inputs and labels through a variational form of mutual information. Thereby, we develop a new form of softmax that also converts a classifier to a mutual information evaluator when the dataset is imbalanced. Experimental results show that the new form leads to better classification accuracy, in particular for imbalanced datasets., Comment: ICML Workshop 2021

We study how to evaluate the quantitative information content of a region within an image for a particular label. To this end, we bridge class activation maps with information theory. We develop an informative class activation map (infoCAM). Given a classification task, infoCAM depict how to accumulate information of partial regions to that of the entire image toward a label. Thus, we can utilise infoCAM to locate the most informative features for a label. When applied to an image classification task, infoCAM performs better than the traditional classification map in the weakly supervised object localisation task. We achieve state-of-the-art results on Tiny-ImageNet., Comment: ICML Workshop 2021

Most existing graph neural networks (GNNs) learn node embeddings using the framework of message passing and aggregation. Such GNNs are incapable of learning relative positions between graph nodes within a graph. To empower GNNs with the awareness of node positions, some nodes are set as anchors. Then, using the distances from a node to the anchors, GNNs can infer relative positions between nodes. However, P-GNNs arbitrarily select anchors, leading to compromising position-awareness and feature extraction. To eliminate this compromise, we demonstrate that selecting evenly distributed and asymmetric anchors is essential. On the other hand, we show that choosing anchors that can aggregate embeddings of all the nodes within a graph is NP-hard. Therefore, devising efficient optimal algorithms in a deterministic approach is practically not feasible. To ensure position-awareness and bypass NP-completeness, we propose Position-Sensing Graph Neural Networks (PSGNNs), learning how to choose anchors in a back-propagatable fashion. Experiments verify the effectiveness of PSGNNs against state-of-the-art GNNs, substantially improving performance on various synthetic and real-world graph datasets while enjoying stable scalability. Specifically, PSGNNs on average boost AUC more than 14% for pairwise node classification and 18% for link prediction over the existing state-of-the-art position-aware methods. Our source code is publicly available at: https://github.com/ZhenyueQin/PSGNN

The prevalent convolutional neural network (CNN) based image denoising methods extract features of images to restore the clean ground truth, achieving high denoising accuracy. However, these methods may ignore the underlying distribution of clean images, inducing distortions or artifacts in denoising results. This paper proposes a new perspective to treat image denoising as a distribution learning and disentangling task. Since the noisy image distribution can be viewed as a joint distribution of clean images and noise, the denoised images can be obtained via manipulating the latent representations to the clean counterpart. This paper also provides a distribution learning based denoising framework. Following this framework, we present an invertible denoising network, FDN, without any assumptions on either clean or noise distributions, as well as a distribution disentanglement method. FDN learns the distribution of noisy images, which is different from the previous CNN based discriminative mapping. Experimental results demonstrate FDN's capacity to remove synthetic additive white Gaussian noise (AWGN) on both category-specific and remote sensing images. Furthermore, the performance of FDN surpasses that of previously published methods in real image denoising with fewer parameters and faster speed. Our code is available at: https://github.com/Yang-Liu1082/FDN.git.

Skeleton sequences are lightweight and compact, and thus are ideal candidates for action recognition on edge devices. Recent skeleton-based action recognition methods extract features from 3D joint coordinates as spatial-temporal cues, using these representations in a graph neural network for feature fusion to boost recognition performance. The use of first- and second-order features, i.e., joint and bone representations, has led to high accuracy. Nonetheless, many models are still confused by actions that have similar motion trajectories. To address these issues, we propose fusing higher-order features in the form of angular encoding into modern architectures to robustly capture the relationships between joints and body parts. This simple fusion with popular spatial-temporal graph neural networks achieves new state-of-the-art accuracy in two large benchmarks, including NTU60 and NTU120, while employing fewer parameters and reduced run time. Our source code is publicly available at: https://github.com/ZhenyueQin/Angular-Skeleton-Encoding., Comment: Accepted by IEEE Transactions on Neural Networks and Learning Systems

Invertible networks have various benefits for image denoising since they are lightweight, information-lossless, and memory-saving during back-propagation. However, applying invertible models to remove noise is challenging because the input is noisy, and the reversed output is clean, following two different distributions. We propose an invertible denoising network, InvDN, to address this challenge. InvDN transforms the noisy input into a low-resolution clean image and a latent representation containing noise. To discard noise and restore the clean image, InvDN replaces the noisy latent representation with another one sampled from a prior distribution during reversion. The denoising performance of InvDN is better than all the existing competitive models, achieving a new state-of-the-art result for the SIDD dataset while enjoying less run time. Moreover, the size of InvDN is far smaller, only having 4.2% of the number of parameters compared to the most recently proposed DANet. Further, via manipulating the noisy latent representation, InvDN is also able to generate noise more similar to the original one. Our code is available at: https://github.com/Yang-Liu1082/InvDN.git.

Pupillary responses (PR) change differently for different types of stimuli. This study aims to check whether observers PR can recognise real and posed smiles from a set of smile images and videos. We showed the smile images and smile videos stimuli to observers, and recorded their pupillary responses considering four different situations, namely paired videos, paired images, single videos, and single images. When the same smiler was viewed by observers in both real and posed smile forms, we refer them as paired; otherwise we use the term single. The primary analysis on pupil data revealed that the differences of pupillary response between real and posed smiles are more significant in case of paired videos compared to others. This result is found from timeline analysis, KS-test, and ANOVA test. Overall, our model can recognise real and posed smiles from observers pupillary responses instead of smilers responses. Our research will be applicable in affective computing and computer-human interaction for measuring emotional authenticity., Comment: 7 pages, 5 figures