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)

The prevalence of vision-threatening eye diseases is a significant global burden, with many cases remaining undiagnosed or diagnosed too late for effective treatment. Large vision-language models (LVLMs) have the potential to assist in understanding anatomical information, diagnosing eye diseases, and drafting interpretations and follow-up plans, thereby reducing the burden on clinicians and improving access to eye care. However, limited benchmarks are available to assess LVLMs' performance in ophthalmology-specific applications. In this study, we introduce LMOD, a large-scale multimodal ophthalmology benchmark consisting of 21,993 instances across (1) five ophthalmic imaging modalities: optical coherence tomography, color fundus photographs, scanning laser ophthalmoscopy, lens photographs, and surgical scenes; (2) free-text, demographic, and disease biomarker information; and (3) primary ophthalmology-specific applications such as anatomical information understanding, disease diagnosis, and subgroup analysis. In addition, we benchmarked 13 state-of-the-art LVLM representatives from closed-source, open-source, and medical domains. The results demonstrate a significant performance drop for LVLMs in ophthalmology compared to other domains. Systematic error analysis further identified six major failure modes: misclassification, failure to abstain, inconsistent reasoning, hallucination, assertions without justification, and lack of domain-specific knowledge. In contrast, supervised neural networks specifically trained on these tasks as baselines demonstrated high accuracy. These findings underscore the pressing need for benchmarks in the development and validation of ophthalmology-specific LVLMs., Comment: Project Page: https://kfzyqin.github.io/lmod/

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

We introduce a pipeline to address anatomical inaccuracies in Stable Diffusion generated hand images. The initial step involves constructing a specialized dataset, focusing on hand anomalies, to train our models effectively. A finetuned detection model is pivotal for precise identification of these anomalies, ensuring targeted correction. Body pose estimation aids in understanding hand orientation and positioning, crucial for accurate anomaly correction. The integration of ControlNet and InstructPix2Pix facilitates sophisticated inpainting and pixel-level transformation, respectively. This dual approach allows for high-fidelity image adjustments. This comprehensive approach ensures the generation of images with anatomically accurate hands, closely resembling real-world appearances. Our experimental results demonstrate the pipeline's efficacy in enhancing hand image realism in Stable Diffusion outputs. We provide an online demo at https://fixhand.yiqun.io

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

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.

Skeleton-based action recognition attracts practitioners and researchers due to the lightweight, compact nature of datasets. Compared with RGB-video-based action recognition, skeleton-based action recognition is a safer way to protect the privacy of subjects while having competitive recognition performance. However, due to improvements in skeleton recognition algorithms as well as motion and depth sensors, more details of motion characteristics can be preserved in the skeleton dataset, leading to potential privacy leakage. We first train classifiers to categorize private information from skeleton trajectories to investigate the potential privacy leakage from skeleton datasets. Our preliminary experiments show that the gender classifier achieves 87% accuracy on average, and the re-identification classifier achieves 80% accuracy on average with three baseline models: Shift-GCN, MS-G3D, and 2s-AGCN. We propose an anonymization framework based on adversarial learning to protect potential privacy leakage from the skeleton dataset. Experimental results show that an anonymized dataset can reduce the risk of privacy leakage while having marginal effects on action recognition performance even with simple anonymizer architectures. The code used in our experiments is available at https://github.com/ml-postech/Skeleton-anonymization/

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

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.

Ever since the advent of AlexNet, designing novel deep neural architectures for different tasks has consistently been a productive research direction. Despite the exceptional performance of various architectures in practice, we study a theoretical question: what is the condition for deep neural architectures to preserve all the information of the input data? Identifying the information lossless condition for deep neural architectures is important, because tasks such as image restoration require keep the detailed information of the input data as much as possible. Using the definition of mutual information, we show that: a deep neural architecture can preserve maximum details about the given data if and only if the architecture is invertible. We verify the advantages of our Invertible Restoring Autoencoder (IRAE) network by comparing it with competitive models on three perturbed image restoration tasks: image denoising, jpeg image decompression and image inpainting. Experimental results show that IRAE consistently outperforms non-invertible ones. Our model even contains far fewer parameters. Thus, it may be worthwhile to try replacing standard components of deep neural architectures, such as residual blocks and ReLU, with their invertible counterparts. We believe our work provides a unique perspective and direction for future deep learning research., Comment: ICONIP 2020

Mutual information is widely applied to learn latent representations of observations, whilst its implication in classification neural networks remain to be better explained. We show that optimising the parameters of classification neural networks with softmax cross-entropy is equivalent to maximising the mutual information between inputs and labels under the balanced data assumption. Through experiments on synthetic and real datasets, we show that softmax cross-entropy can estimate mutual information approximately. When applied to image classification, this relation helps approximate the point-wise mutual information between an input image and a label without modifying the network structure. To this end, we propose infoCAM, informative class activation map, which highlights regions of the input image that are the most relevant to a given label based on differences in information. The activation map helps localise the target object in an input image. Through experiments on the semi-supervised object localisation task with two real-world datasets, we evaluate the effectiveness of our information-theoretic approach.

Despite great popularity of applying softmax to map the non-normalised outputs of a neural network to a probability distribution over predicting classes, this normalised exponential transformation still seems to be artificial. A theoretic framework that incorporates softmax as an intrinsic component is still lacking. In this paper, we view neural networks embedding softmax from an information-theoretic perspective. Under this view, we can naturally and mathematically derive log-softmax as an inherent component in a neural network for evaluating the conditional mutual information between network output vectors and labels given an input datum. We show that training deterministic neural networks through maximising log-softmax is equivalent to enlarging the conditional mutual information, i.e., feeding label information into network outputs. We also generalise our informative-theoretic perspective to neural networks with stochasticity and derive information upper and lower bounds of log-softmax. In theory, such an information-theoretic view offers rationality support for embedding softmax in neural networks; in practice, we eventually demonstrate a computer vision application example of how to employ our information-theoretic view to filter out targeted objects on images., Comment: Withdrawn due to Zhenyue Qin uploading the manuscript without consent of the other authors

Human eyes concentrate different facial regions during distinct cognitive activities. We study utilising facial visual saliency maps to classify different facial expressions into different emotions. Our results show that our novel method of merely using facial saliency maps can achieve a descent accuracy of 65\%, much higher than the chance level of $1/7$. Furthermore, our approach is of semi-supervision, i.e., our facial saliency maps are generated from a general saliency prediction algorithm that is not explicitly designed for face images. We also discovered that the classification accuracies of each emotional class using saliency maps demonstrate a strong positive correlation with the accuracies produced by face images. Our work implies that humans may look at different facial areas in order to perceive different emotions.

Eye movement patterns reflect human latent internal cognitive activities. We aim to discover eye movement patterns during face recognition under different cognitions of information concealing. These cognitions include the degrees of face familiarity and deception or not, namely telling the truth when observing familiar and unfamiliar faces, and deceiving in front of familiar faces. We apply Hidden Markov models with Gaussian emission to generalize regions and trajectories of eye fixation points under the above three conditions. Our results show that both eye movement patterns and eye gaze regions become significantly different during deception compared with truth-telling. We show the feasibility of detecting deception and further cognitive activity classification using eye movement patterns.

Crowd predictions have demonstrated powerful performance in predicting future events. We aim to understand crowd prediction efficacy in ascertaining the veracity of human emotional expressions. We discover that collective discernment can increase the accuracy of detecting emotion veracity from 63%, which is the average individual performance, to 80%. Constraining data to best performers can further increase the result up to 92%. Neural networks can achieve an accuracy to 99.69% by aggregating participants' answers. That is, assigning positive and negative weights to high and low human predictors, respectively. Furthermore, neural networks that are trained with one emotion data can also produce high accuracies on discerning the veracity of other emotion types: our crowdsourced transfer of emotion learning is novel. We find that our neural networks do not require a large number of participants, particularly, 30 randomly selected, to achieve high accuracy predictions, better than any individual participant. Our proposed method of assembling peoples' predictions with neural networks can provide insights for applications such as fake news prevention and lie detection.

Wagner's modularity inducing problem domain is a key contribution to the study of the evolution of modularity, including both evolutionary theory and evolutionary computation. We study its behavior under classical genetic algorithms. Unlike what we seem to observe in nature, the emergence of modularity is highly conditional and dependent, for example, on the eagerness of search. In nature, modular solutions generally dominate populations, whereas in this domain, modularity, when it emerges, is a relatively rare variant. Emergence of modularity depends heavily on random fluctuations in the fitness function, with a randomly varied but unchanging fitness function, modularity evolved far more rarely. Interestingly, high-fitness non-modular solutions could frequently be converted into even-higher-fitness modular solutions by manually removing all inter-module edges. Despite careful exploration, we do not yet have a full explanation of why the genetic algorithm was unable to find these better solutions.