Search

With the advent of Large Language Models (LLMs) and Multimodal (Visio-lingual) LLMs, a flurry of research has emerged, analyzing the performance of such models across a diverse array of tasks. While most studies focus on evaluating the capabilities of state-of-the-art (SoTA) MLLM models through task accuracy (e.g., Visual Question Answering, grounding) across various datasets, our work explores the related but complementary aspect of consistency - the ability of an MLLM model to produce semantically similar or identical responses to semantically similar queries. We note that consistency is a fundamental prerequisite (necessary but not sufficient condition) for robustness and trust in MLLMs. Humans, in particular, are known to be highly consistent (even if not always accurate) in their responses, and consistency is inherently expected from AI systems. Armed with this perspective, we propose the MM-R$^3$ benchmark, which analyses the performance in terms of consistency and accuracy in SoTA MLLMs with three tasks: Question Rephrasing, Image Restyling, and Context Reasoning. Our analysis reveals that consistency does not always align with accuracy, indicating that models with higher accuracy are not necessarily more consistent, and vice versa. Furthermore, we propose a simple yet effective mitigation strategy in the form of an adapter module trained to minimize inconsistency across prompts. With our proposed strategy, we are able to achieve absolute improvements of 5.7% and 12.5%, on average on widely used MLLMs such as BLIP-2 and LLaVa 1.5M in terms of consistency over their existing counterparts.

The emergence of attention-based transformer models has led to their extensive use in various tasks, due to their superior generalization and transfer properties. Recent research has demonstrated that such models, when prompted appropriately, are excellent for few-shot inference. However, such techniques are under-explored for dense prediction tasks like semantic segmentation. In this work, we examine the effectiveness of prompting a transformer-decoder with learned visual prompts for the generalized few-shot segmentation (GFSS) task. Our goal is to achieve strong performance not only on novel categories with limited examples, but also to retain performance on base categories. We propose an approach to learn visual prompts with limited examples. These learned visual prompts are used to prompt a multiscale transformer decoder to facilitate accurate dense predictions. Additionally, we introduce a unidirectional causal attention mechanism between the novel prompts, learned with limited examples, and the base prompts, learned with abundant data. This mechanism enriches the novel prompts without deteriorating the base class performance. Overall, this form of prompting helps us achieve state-of-the-art performance for GFSS on two different benchmark datasets: COCO-$20^i$ and Pascal-$5^i$, without the need for test-time optimization (or transduction). Furthermore, test-time optimization leveraging unlabelled test data can be used to improve the prompts, which we refer to as transductive prompt tuning., Comment: Accepted at CVPR 2024

Existing dense or paragraph video captioning approaches rely on holistic representations of videos, possibly coupled with learned object/action representations, to condition hierarchical language decoders. However, they fundamentally lack the commonsense knowledge of the world required to reason about progression of events, causality, and even the function of certain objects within a scene. To address this limitation we propose a novel video captioning Transformer-based model, that takes into account both implicit (visuo-lingual and purely linguistic) and explicit (knowledge-base) commonsense knowledge. We show that these forms of knowledge, in isolation and in combination, enhance the quality of produced captions. Further, inspired by imitation learning, we propose a new task of instruction generation, where the goal is to produce a set of linguistic instructions from a video demonstration of its performance. We formalize the task using the ALFRED dataset [54] generated using an AI2-THOR environment. While instruction generation is conceptually similar to paragraph captioning, it differs in the fact that it exhibits stronger object persistence, as well as spatially-aware and causal sentence structure. We show that our commonsense knowledge enhanced approach produces significant improvements on this task (up to 57% in METEOR and 8.5% in CIDEr), as well as the state-of-the-art result on more traditional video captioning in the ActivityNet Captions dataset [29]., Comment: The paper is under consideration at Computer Vision and Image Understanding Journal

Recent advances in pixel-level tasks (e.g. segmentation) illustrate the benefit of of long-range interactions between aggregated region-based representations that can enhance local features. However, such aggregated representations, often in the form of attention, fail to model the underlying semantics of the scene (e.g. individual objects and, by extension, their interactions). In this work, we address the issue by proposing a component that learns to project image features into latent representations and reason between them using a transformer encoder to generate contextualized and scene-consistent representations which are fused with original image features. Our design encourages the latent regions to represent semantic concepts by ensuring that the activated regions are spatially disjoint and the union of such regions corresponds to a connected object segment. The proposed semantic global reasoning (SGR) component is end-to-end trainable and can be easily added to a wide variety of backbones (CNN or transformer-based) and segmentation heads (per-pixel or mask classification) to consistently improve the segmentation results on different datasets. In addition, our latent tokens are semantically interpretable and diverse and provide a rich set of features that can be transferred to downstream tasks like object detection and segmentation, with improved performance. Furthermore, we also proposed metrics to quantify the semantics of latent tokens at both class \& instance level., Comment: Published in WACV 2024

We propose a bootstrapping framework to enhance human optical flow and pose. We show that, for videos involving humans in scenes, we can improve both the optical flow and the pose estimation quality of humans by considering the two tasks at the same time. We enhance optical flow estimates by fine-tuning them to fit the human pose estimates and vice versa. In more detail, we optimize the pose and optical flow networks to, at inference time, agree with each other. We show that this results in state-of-the-art results on the Human 3.6M and 3D Poses in the Wild datasets, as well as a human-related subset of the Sintel dataset, both in terms of pose estimation accuracy and the optical flow accuracy at human joint locations. Code available at https://github.com/ubc-vision/bootstrapping-human-optical-flow-and-pose, Comment: Accepted at BMVC 2022. Supplementary qualitative results - https://aritro30.github.io/results/. Code at https://github.com/ubc-vision/bootstrapping-human-optical-flow-and-pose

Neural Radiance Fields (NeRFs) increase reconstruction detail for novel view synthesis and scene reconstruction, with applications ranging from large static scenes to dynamic human motion. However, the increased resolution and model-free nature of such neural fields come at the cost of high training times and excessive memory requirements. Recent advances improve the inference time by using complementary data structures yet these methods are ill-suited for dynamic scenes and often increase memory consumption. Little has been done to reduce the resources required at training time. We propose a method to exploit the redundancy of NeRF's sample-based computations by partially sharing evaluations across neighboring sample points. Our UNeRF architecture is inspired by the UNet, where spatial resolution is reduced in the middle of the network and information is shared between adjacent samples. Although this change violates the strict and conscious separation of view-dependent appearance and view-independent density estimation in the NeRF method, we show that it improves novel view synthesis. We also introduce an alternative subsampling strategy which shares computation while minimizing any violation of view invariance. UNeRF is a plug-in module for the original NeRF network. Our major contributions include reduction of the memory footprint, improved accuracy, and reduced amortized processing time both during training and inference. With only weak assumptions on locality, we achieve improved resource utilization on a variety of neural radiance fields tasks. We demonstrate applications to the novel view synthesis of static scenes as well as dynamic human shape and motion.

Human pose estimation from single images is a challenging problem that is typically solved by supervised learning. Unfortunately, labeled training data does not yet exist for many human activities since 3D annotation requires dedicated motion capture systems. Therefore, we propose an unsupervised approach that learns to predict a 3D human pose from a single image while only being trained with 2D pose data, which can be crowd-sourced and is already widely available. To this end, we estimate the 3D pose that is most likely over random projections, with the likelihood estimated using normalizing flows on 2D poses. While previous work requires strong priors on camera rotations in the training data set, we learn the distribution of camera angles which significantly improves the performance. Another part of our contribution is to stabilize training with normalizing flows on high-dimensional 3D pose data by first projecting the 2D poses to a linear subspace. We outperform the state-of-the-art unsupervised human pose estimation methods on the benchmark datasets Human3.6M and MPI-INF-3DHP in many metrics.

The problem of language grounding has attracted much attention in recent years due to its pivotal role in more general image-lingual high level reasoning tasks (e.g., image captioning, VQA). Despite the tremendous progress in visual grounding, the performance of most approaches has been hindered by the quality of bounding box proposals obtained in the early stages of all recent pipelines. To address this limitation, we propose a general progressive query-guided bounding box refinement architecture (OptiBox) that leverages global image encoding for added context. We apply this architecture in the context of the GroundeR model, first introduced in 2016, which has a number of unique and appealing properties, such as the ability to learn in the semi-supervised setting by leveraging cyclic language-reconstruction. Using GroundeR + OptiBox and a simple semantic language reconstruction loss that we propose, we achieve state-of-the-art grounding performance in the supervised setting on Flickr30k Entities dataset. More importantly, we are able to surpass many recent fully supervised models with only 50% of training data and perform competitively with as low as 3%.

We present an online SLAM system specifically designed to track pan-tilt-zoom (PTZ) cameras in highly dynamic sports such as basketball and soccer games. In these games, PTZ cameras rotate very fast and players cover large image areas. To overcome these challenges, we propose to use a novel camera model for tracking and to use rays as landmarks in mapping. Rays overcome the missing depth in pure-rotation cameras. We also develop an online pan-tilt forest for mapping and introduce moving objects (players) detection to mitigate negative impacts from foreground objects. We test our method on both synthetic and real datasets. The experimental results show the superior performance of our method over previous methods for online PTZ camera pose estimation., Comment: 10+3 pages, BMVC 2019 accepted

Calibrating sports cameras is important for autonomous broadcasting and sports analysis. Here we propose a highly automatic method for calibrating sports cameras from a single image using synthetic data. First, we develop a novel camera pose engine. The camera pose engine has only three significant free parameters so that it can effectively generate a lot of camera poses and corresponding edge (i.e, field marking) images. Then, we learn compact deep features via a siamese network from paired edge image and camera pose and build a feature-pose database. After that, we use a novel two-GAN (generative adversarial network) model to detect field markings in real images. Finally, we query an initial camera pose from the feature-pose database and refine camera poses using truncated distance images. We evaluate our method on both synthetic and real data. Our method not only demonstrates the robustness on the synthetic data but also achieves the state-of-the-art accuracy on a standard soccer dataset and very high performance on a volleyball dataset., Comment: 6 + 1 pages

In the real world, a learning system could receive an input that is unlike anything it has seen during training. Unfortunately, out-of-distribution samples can lead to unpredictable behaviour. We need to know whether any given input belongs to the population distribution of the training/evaluation data to prevent unpredictable behaviour in deployed systems. A recent surge of interest in this problem has led to the development of sophisticated techniques in the deep learning literature. However, due to the absence of a standard problem definition or an exhaustive evaluation, it is not evident if we can rely on these methods. What makes this problem different from a typical supervised learning setting is that the distribution of outliers used in training may not be the same as the distribution of outliers encountered in the application. Classical approaches that learn inliers vs. outliers with only two datasets can yield optimistic results. We introduce OD-test, a three-dataset evaluation scheme as a more reliable strategy to assess progress on this problem. We present an exhaustive evaluation of a broad set of methods from related areas on image classification tasks. Contrary to the existing results, we show that for realistic applications of high-dimensional images the previous techniques have low accuracy and are not reliable in practice., Comment: to appear in BMVC 2019; v2 is more compact, with more results

This work addresses camera selection, the task of predicting which camera should be "on air" from multiple candidate cameras for soccer broadcast. The task is challenging because of the scarcity of learning data with all candidate views. Meanwhile, broadcast videos are freely available on the Internet (e.g. Youtube). However, these videos only record the selected camera views, omitting the other candidate views. To overcome this problem, we first introduce a random survival forest (RSF) method to impute the incomplete data effectively. Then, we propose a spatial-appearance heatmap to describe foreground objects (e.g. players and balls) in an image. To evaluate the performance of our system, we collect the largest-ever dataset for soccer broadcasting camera selection. It has one main game which has all candidate views and twelve auxiliary games which only have the broadcast view. Our method significantly outperforms state-of-the-art methods on this challenging dataset. Further analysis suggests that the improvement in performance is indeed from the extra information from auxiliary games., Comment: 8 + 2 pages, WACV2019 accepted

Calibrating narrow field of view soccer cameras is challenging because there are very few field markings in the image. Unlike previous solutions, we propose a two-point method, which requires only two point correspondences given the prior knowledge of base location and orientation of a pan-tilt-zoom (PTZ) camera. We deploy this new calibration method to annotate pan-tilt-zoom data from soccer videos. The collected data are used as references for new images. We also propose a fast random forest method to predict pan-tilt angles without image-to-image feature matching, leading to an efficient calibration method for new images. We demonstrate our system on synthetic data and two real soccer datasets. Our two-point approach achieves superior performance over the state-of-the-art method., Comment: WACV 2018 accepted

In this work, we address the problem of 3D human pose estimation from a sequence of 2D human poses. Although the recent success of deep networks has led many state-of-the-art methods for 3D pose estimation to train deep networks end-to-end to predict from images directly, the top-performing approaches have shown the effectiveness of dividing the task of 3D pose estimation into two steps: using a state-of-the-art 2D pose estimator to estimate the 2D pose from images and then mapping them into 3D space. They also showed that a low-dimensional representation like 2D locations of a set of joints can be discriminative enough to estimate 3D pose with high accuracy. However, estimation of 3D pose for individual frames leads to temporally incoherent estimates due to independent error in each frame causing jitter. Therefore, in this work we utilize the temporal information across a sequence of 2D joint locations to estimate a sequence of 3D poses. We designed a sequence-to-sequence network composed of layer-normalized LSTM units with shortcut connections connecting the input to the output on the decoder side and imposed temporal smoothness constraint during training. We found that the knowledge of temporal consistency improves the best reported result on Human3.6M dataset by approximately $12.2\%$ and helps our network to recover temporally consistent 3D poses over a sequence of images even when the 2D pose detector fails.

Camera relocalization plays a vital role in many robotics and computer vision tasks, such as global localization, recovery from tracking failure and loop closure detection. Recent random forests based methods exploit randomly sampled pixel comparison features to predict 3D world locations for 2D image locations to guide the camera pose optimization. However, these image features are only sampled randomly in the images, without considering the spatial structures or geometric information, leading to large errors or failure cases with the existence of poorly textured areas or in motion blur. Line segment features are more robust in these environments. In this work, we propose to jointly exploit points and lines within the framework of uncertainty driven regression forests. The proposed approach is thoroughly evaluated on three publicly available datasets against several strong state-of-the-art baselines in terms of several different error metrics. Experimental results prove the efficacy of our method, showing superior or on-par state-of-the-art performance., Comment: published as a conference paper at 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Camera relocalization plays a vital role in many robotics and computer vision tasks, such as global localization, recovery from tracking failure, and loop closure detection. Recent random forests based methods directly predict 3D world locations for 2D image locations to guide the camera pose optimization. During training, each tree greedily splits the samples to minimize the spatial variance. However, these greedy splits often produce uneven sub-trees in training or incorrect 2D-3D correspondences in testing. To address these problems, we propose a sample-balanced objective to encourage equal numbers of samples in the left and right sub-trees, and a novel backtracking scheme to remedy the incorrect 2D-3D correspondence predictions. Furthermore, we extend the regression forests based methods to use local features in both training and testing stages for outdoor RGB-only applications. Experimental results on publicly available indoor and outdoor datasets demonstrate the efficacy of our approach, which shows superior or on-par accuracy with several state-of-the-art methods., Comment: 8 pages. Appear in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2017

Vision based player detection is important in sports applications. Accuracy, efficiency, and low memory consumption are desirable for real-time tasks such as intelligent broadcasting and automatic event classification. In this paper, we present a cascaded convolutional neural network (CNN) that satisfies all three of these requirements. Our method first trains a binary (player/non-player) classification network from labeled image patches. Then, our method efficiently applies the network to a whole image in testing. We conducted experiments on basketball and soccer games. Experimental results demonstrate that our method can accurately detect players under challenging conditions such as varying illumination, highly dynamic camera movements and motion blur. Comparing with conventional CNNs, our approach achieves state-of-the-art accuracy on both games with 1000x fewer parameters (i.e., it is light}., Comment: Published in proceedings of BMVC 2017

Following the success of deep convolutional networks, state-of-the-art methods for 3d human pose estimation have focused on deep end-to-end systems that predict 3d joint locations given raw image pixels. Despite their excellent performance, it is often not easy to understand whether their remaining error stems from a limited 2d pose (visual) understanding, or from a failure to map 2d poses into 3-dimensional positions. With the goal of understanding these sources of error, we set out to build a system that given 2d joint locations predicts 3d positions. Much to our surprise, we have found that, with current technology, "lifting" ground truth 2d joint locations to 3d space is a task that can be solved with a remarkably low error rate: a relatively simple deep feed-forward network outperforms the best reported result by about 30\% on Human3.6M, the largest publicly available 3d pose estimation benchmark. Furthermore, training our system on the output of an off-the-shelf state-of-the-art 2d detector (\ie, using images as input) yields state of the art results -- this includes an array of systems that have been trained end-to-end specifically for this task. Our results indicate that a large portion of the error of modern deep 3d pose estimation systems stems from their visual analysis, and suggests directions to further advance the state of the art in 3d human pose estimation., Comment: Accepted to ICCV 17

Video games are a compelling source of annotated data as they can readily provide fine-grained groundtruth for diverse tasks. However, it is not clear whether the synthetically generated data has enough resemblance to the real-world images to improve the performance of computer vision models in practice. We present experiments assessing the effectiveness on real-world data of systems trained on synthetic RGB images that are extracted from a video game. We collected over 60000 synthetic samples from a modern video game with similar conditions to the real-world CamVid and Cityscapes datasets. We provide several experiments to demonstrate that the synthetically generated RGB images can be used to improve the performance of deep neural networks on both image segmentation and depth estimation. These results show that a convolutional network trained on synthetic data achieves a similar test error to a network that is trained on real-world data for dense image classification. Furthermore, the synthetically generated RGB images can provide similar or better results compared to the real-world datasets if a simple domain adaptation technique is applied. Our results suggest that collaboration with game developers for an accessible interface to gather data is potentially a fruitful direction for future work in computer vision., Comment: To appear in the British Machine Vision Conference (BMVC), September 2016. -v2: fixed a typo in the references

Commonly used human motion capture systems require intrusive attachment of markers that are visually tracked with multiple cameras. In this work we present an efficient and inexpensive solution to markerless motion capture using only a few Kinect sensors. Unlike the previous work on 3d pose estimation using a single depth camera, we relax constraints on the camera location and do not assume a co-operative user. We apply recent image segmentation techniques to depth images and use curriculum learning to train our system on purely synthetic data. Our method accurately localizes body parts without requiring an explicit shape model. The body joint locations are then recovered by combining evidence from multiple views in real-time. We also introduce a dataset of ~6 million synthetic depth frames for pose estimation from multiple cameras and exceed state-of-the-art results on the Berkeley MHAD dataset., Comment: Accepted to computer robot vision 2016

Recently, Babenko and Lempitsky introduced Additive Quantization (AQ), a generalization of Product Quantization (PQ) where a non-independent set of codebooks is used to compress vectors into small binary codes. Unfortunately, under this scheme encoding cannot be done independently in each codebook, and optimal encoding is an NP-hard problem. In this paper, we observe that PQ and AQ are both compositional quantizers that lie on the extremes of the codebook dependence-independence assumption, and explore an intermediate approach that exploits a hierarchical structure in the codebooks. This results in a method that achieves quantization error on par with or lower than AQ, while being several orders of magnitude faster. We perform a complexity analysis of PQ, AQ and our method, and evaluate our approach on standard benchmarks of SIFT and GIST descriptors, as well as on new datasets of features obtained from state-of-the-art convolutional neural networks.

This paper introduces a novel self-learning framework that automates the label acquisition process for improving models for detecting players in broadcast footage of sports games. Unlike most previous self-learning approaches for improving appearance-based object detectors from videos, we allow an unknown, unconstrained number of target objects in a more generalized video sequence with non-static camera views. Our self-learning approach uses a latent SVM learning algorithm and deformable part models to represent the shape and colour information of players, constraining their motions, and learns the colour of the playing field by a gentle Adaboost algorithm. We combine those image cues and discover additional labels automatically from unlabelled data. In our experiments, our approach exploits both labelled and unlabelled data in sparsely labelled videos of sports games, providing a mean performance improvement of over 20% in the average precision for detecting sports players and improved tracking, when videos contain very few labelled images.