Event Stream based Sign Language Translation: A High-Definition Benchmark Dataset and A New Algorithm

Sign Language Translation (SLT) is a core task in the field of AI-assisted disability. Unlike traditional SLT based on visible light videos, which is easily affected by factors such as lighting, rapid hand movements, and privacy breaches, this paper proposes the use of high-definition Event streams for SLT, effectively mitigating the aforementioned issues. This is primarily because Event streams have a high dynamic range and dense temporal signals, which can withstand low illumination and motion blur well. Additionally, due to their sparsity in space, they effectively protect the privacy of the target person. More specifically, we propose a new high-resolution Event stream sign language dataset, termed Event-CSL, which effectively fills the data gap in this area of research. It contains 14,827 videos, 14,821 glosses, and 2,544 Chinese words in the text vocabulary. These samples are collected in a variety of indoor and outdoor scenes, encompassing multiple angles, light intensities, and camera movements. We have benchmarked existing mainstream SLT works to enable fair comparison for future efforts. Based on this dataset and several other large-scale datasets, we propose a novel baseline method that fully leverages the Mamba model's ability to integrate temporal information of CNN features, resulting in improved sign language translation outcomes. Both the benchmark dataset and source code will be released on https://github.com/Event-AHU/OpenESL

Classifier Guidance Enhances Diffusion-based Adversarial Purification by Preserving Predictive Information

Adversarial purification is one of the promising approaches to defend neural networks against adversarial attacks. Recently, methods utilizing diffusion probabilistic models have achieved great success for adversarial purification in image classification tasks. However, such methods fall into the dilemma of balancing the needs for noise removal and information preservation. This paper points out that existing adversarial purification methods based on diffusion models gradually lose sample information during the core denoising process, causing occasional label shift in subsequent classification tasks. As a remedy, we suggest to suppress such information loss by introducing guidance from the classifier confidence. Specifically, we propose Classifier-cOnfidence gUided Purification (COUP) algorithm, which purifies adversarial examples while keeping away from the classifier decision boundary. Experimental results show that COUP can achieve better adversarial robustness under strong attack methods.

3D-UGCN: A Unified Graph Convolutional Network for Robust 3D Human Pose Estimation from Monocular RGB Images

Human pose estimation remains a multifaceted challenge in computer vision, pivotal across diverse domains such as behavior recognition, human-computer interaction, and pedestrian tracking. This paper proposes an improved method based on the spatial-temporal graph convolution net-work (UGCN) to address the issue of missing human posture skeleton sequences in single-view videos. We present the improved UGCN, which allows the network to process 3D human pose data and improves the 3D human pose skeleton sequence, thereby resolving the occlusion issue.

Dissecting Multiplication in Transformers: Insights into LLMs

Transformer-based large language models have achieved remarkable performance across various natural language processing tasks. However, they often struggle with seemingly easy tasks like arithmetic despite their vast capabilities. This stark disparity raise human's concerns about their safe and ethical use, hinder their widespread adoption.In this paper, we focus on a typical arithmetic task, integer multiplication, to explore and explain the imperfection of transformers in this domain. We provide comprehensive analysis of a vanilla transformer trained to perform n-digit integer multiplication. Our observations indicate that the model decomposes multiplication task into multiple parallel subtasks, sequentially optimizing each subtask for each digit to complete the final multiplication. Based on observation and analysis, we infer the reasons of transformers deficiencies in multiplication tasks lies in their difficulty in calculating successive carryovers and caching intermediate results, and confirmed this inference through experiments. Guided by these findings, we propose improvements to enhance transformers performance on multiplication tasks. These enhancements are validated through rigorous testing and mathematical modeling, not only enhance transformer's interpretability, but also improve its performance, e.g., we achieve over 99.9% accuracy on 5-digit integer multiplication with a tiny transformer, outperform LLMs GPT-4. Our method contributes to the broader fields of model understanding and interpretability, paving the way for analyzing more complex tasks and Transformer models. This work underscores the importance of explainable AI, helping to build trust in large language models and promoting their adoption in critical applications.

Technique Report of CVPR 2024 PBDL Challenges

The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies. By leveraging the principles of physics to inform and enhance deep learning models, we can develop more robust and accurate vision systems. Physics-based vision aims to invert the processes to recover scene properties such as shape, reflectance, light distribution, and medium properties from images. In recent years, deep learning has shown promising improvements for various vision tasks, and when combined with physics-based vision, these approaches can enhance the robustness and accuracy of vision systems. This technical report summarizes the outcomes of the Physics-Based Vision Meets Deep Learning (PBDL) 2024 challenge, held in CVPR 2024 workshop. The challenge consisted of eight tracks, focusing on Low-Light Enhancement and Detection as well as High Dynamic Range (HDR) Imaging. This report details the objectives, methodologies, and results of each track, highlighting the top-performing solutions and their innovative approaches.

XPose: eXplainable Human Pose Estimation

Current approaches in pose estimation primarily concentrate on enhancing model architectures, often overlooking the importance of comprehensively understanding the rationale behind model decisions. In this paper, we propose XPose, a novel framework that incorporates Explainable AI (XAI) principles into pose estimation. This integration aims to elucidate the individual contribution of each keypoint to final prediction, thereby elevating the model's transparency and interpretability. Conventional XAI techniques have predominantly addressed tasks with single-target tasks like classification. Additionally, the application of Shapley value, a common measure in XAI, to pose estimation has been hindered by prohibitive computational demands. To address these challenges, this work introduces an innovative concept called Group Shapley Value (GSV). This approach strategically organizes keypoints into clusters based on their interdependencies. Within these clusters, GSV meticulously calculates Shapley value for keypoints, while for inter-cluster keypoints, it opts for a more holistic group-level valuation. This dual-level computation framework meticulously assesses keypoint contributions to the final outcome, optimizing computational efficiency. Building on the insights into keypoint interactions, we devise a novel data augmentation technique known as Group-based Keypoint Removal (GKR). This method ingeniously removes individual keypoints during training phases, deliberately preserving those with strong mutual connections, thereby refining the model's predictive prowess for non-visible keypoints. The empirical validation of GKR across a spectrum of standard approaches attests to its efficacy. GKR's success demonstrates how using Explainable AI (XAI) can directly enhance pose estimation models.

Proximity QA: Unleashing the Power of Multi-Modal Large Language Models for Spatial Proximity Analysis

Multi-modal large language models (MLLMs) have demonstrated remarkable vision-language capabilities, primarily due to the exceptional in-context understanding and multi-task learning strengths of large language models (LLMs). The advent of visual instruction tuning has further enhanced MLLMs' performance in vision-language understanding. However, while existing MLLMs adeptly recognize \textit{what} objects are in an image, they still face challenges in effectively discerning \textit{where} these objects are, particularly along the distance (scene depth) axis. To overcome this limitation in MLLMs, we introduce Proximity Question Answering (Proximity QA), a novel framework designed to enable MLLMs to infer the proximity relationship between objects in images. The framework operates in two phases: the first phase focuses on guiding the models to understand the relative depth of objects, and the second phase further encourages the models to infer the proximity relationships between objects based on their depth perceptions. We also propose a VQA dataset called Proximity-110K, containing additional instructions that incorporate depth information and the proximity relationships of objects. We have conducted extensive experiments to validate Proximity QA's superior ability in depth perception and proximity analysis, outperforming other state-of-the-art MLLMs. Code and dataset will be released at \textcolor{magenta}{https://github.com/NorthSummer/ProximityQA.git}.

Residual Alignment: Uncovering the Mechanisms of Residual Networks

The ResNet architecture has been widely adopted in deep learning due to its significant boost to performance through the use of simple skip connections, yet the underlying mechanisms leading to its success remain largely unknown. In this paper, we conduct a thorough empirical study of the ResNet architecture in classification tasks by linearizing its constituent residual blocks using Residual Jacobians and measuring their singular value decompositions. Our measurements reveal a process called Residual Alignment (RA) characterized by four properties: (RA1) intermediate representations of a given input are equispaced on a line, embedded in high dimensional space, as observed by Gai and Zhang [2021]; (RA2) top left and right singular vectors of Residual Jacobians align with each other and across different depths; (RA3) Residual Jacobians are at most rank C for fully-connected ResNets, where C is the number of classes; and (RA4) top singular values of Residual Jacobians scale inversely with depth. RA consistently occurs in models that generalize well, in both fully-connected and convolutional architectures, across various depths and widths, for varying numbers of classes, on all tested benchmark datasets, but ceases to occur once the skip connections are removed. It also provably occurs in a novel mathematical model we propose. This phenomenon reveals a strong alignment between residual branches of a ResNet (RA2+4), imparting a highly rigid geometric structure to the intermediate representations as they progress linearly through the network (RA1) up to the final layer, where they undergo Neural Collapse.

SODFormer: Streaming Object Detection with Transformer Using Events and Frames

DAVIS camera, streaming two complementary sensing modalities of asynchronous events and frames, has gradually been used to address major object detection challenges (e.g., fast motion blur and low-light). However, how to effectively leverage rich temporal cues and fuse two heterogeneous visual streams remains a challenging endeavor. To address this challenge, we propose a novel streaming object detector with Transformer, namely SODFormer, which first integrates events and frames to continuously detect objects in an asynchronous manner. Technically, we first build a large-scale multimodal neuromorphic object detection dataset (i.e., PKU-DAVIS-SOD) over 1080.1k manual labels. Then, we design a spatiotemporal Transformer architecture to detect objects via an end-to-end sequence prediction problem, where the novel temporal Transformer module leverages rich temporal cues from two visual streams to improve the detection performance. Finally, an asynchronous attention-based fusion module is proposed to integrate two heterogeneous sensing modalities and take complementary advantages from each end, which can be queried at any time to locate objects and break through the limited output frequency from synchronized frame-based fusion strategies. The results show that the proposed SODFormer outperforms four state-of-the-art methods and our eight baselines by a significant margin. We also show that our unifying framework works well even in cases where the conventional frame-based camera fails, e.g., high-speed motion and low-light conditions. Our dataset and code can be available at https://github.com/dianzl/SODFormer.

Deep Directly-Trained Spiking Neural Networks for Object Detection

Spiking neural networks (SNNs) are brain-inspired energy-efficient models that encode information in spatiotemporal dynamics. Recently, deep SNNs trained directly have shown great success in achieving high performance on classification tasks with very few time steps. However, how to design a directly-trained SNN for the regression task of object detection still remains a challenging problem. To address this problem, we propose EMS-YOLO, a novel directly-trained SNN framework for object detection, which is the first trial to train a deep SNN with surrogate gradients for object detection rather than ANN-SNN conversion strategies. Specifically, we design a full-spike residual block, EMS-ResNet, which can effectively extend the depth of the directly-trained SNN with low power consumption. Furthermore, we theoretically analyze and prove the EMS-ResNet could avoid gradient vanishing or exploding. The results demonstrate that our approach outperforms the state-of-the-art ANN-SNN conversion methods (at least 500 time steps) in extremely fewer time steps (only 4 time steps). It is shown that our model could achieve comparable performance to the ANN with the same architecture while consuming 5.83 times less energy on the frame-based COCO Dataset and the event-based Gen1 Dataset.