In sign language, the conveyance of human body trajectories predominantly relies upon the coordinated movements of hands and facial expressions across successive frames. Despite the recent advancements of sign language understanding methods, they often solely focus on individual frames, inevitably overlooking the inter-frame correlations that are essential for effectively modeling human body trajectories. To address this limitation, this paper introduces a spatial-temporal correlation network, denoted as CorrNet+, which explicitly identifies body trajectories across multiple frames. In specific, CorrNet+ employs a correlation module and an identification module to build human body trajectories. Afterwards, a temporal attention module is followed to adaptively evaluate the contributions of different frames. The resultant features offer a holistic perspective on human body movements, facilitating a deeper understanding of sign language. As a unified model, CorrNet+ achieves new state-of-the-art performance on two extensive sign language understanding tasks, including continuous sign language recognition (CSLR) and sign language translation (SLT). Especially, CorrNet+ surpasses previous methods equipped with resource-intensive pose-estimation networks or pre-extracted heatmaps for hand and facial feature extraction. Compared with CorrNet, CorrNet+ achieves a significant performance boost across all benchmarks while halving the computational overhead. A comprehensive comparison with previous spatial-temporal reasoning methods verifies the superiority of CorrNet+. Code is available at https://github.com/hulianyuyy/CorrNet_Plus.
The advent of edge computing has made real-time intelligent video analytics feasible. Previous works, based on traditional model architecture (e.g., CNN, RNN, etc.), employ various strategies to filter out non-region-of-interest content to minimize bandwidth and computation consumption but show inferior performance in adverse environments. Recently, visual foundation models based on transformers have shown great performance in adverse environments due to their amazing generalization capability. However, they require a large amount of computation power, which limits their applications in real-time intelligent video analytics. In this paper, we find visual foundation models like Vision Transformer (ViT) also have a dedicated acceleration mechanism for video analytics. To this end, we introduce Arena, an end-to-end edge-assisted video inference acceleration system based on ViT. We leverage the capability of ViT that can be accelerated through token pruning by only offloading and feeding Patches-of-Interest (PoIs) to the downstream models. Additionally, we employ probability-based patch sampling, which provides a simple but efficient mechanism for determining PoIs where the probable locations of objects are in subsequent frames. Through extensive evaluations on public datasets, our findings reveal that Arena can boost inference speeds by up to $1.58\times$ and $1.82\times$ on average while consuming only 54% and 34% of the bandwidth, respectively, all with high inference accuracy.
The increase of web-scale weakly labelled image-text pairs have greatly facilitated the development of large-scale vision-language models (e.g., CLIP), which have shown impressive generalization performance over a series of downstream tasks. However, the massive model size and scarcity of available data limit their applications to fine-tune the whole model in downstream tasks. Besides, fully fine-tuning the model easily forgets the generic essential knowledge acquired in the pretraining stage and overfits the downstream data. To enable high efficiency when adapting these large vision-language models (e.g., CLIP) to performing continuous sign language recognition (CSLR) while preserving their generalizability, we propose a novel strategy (AdaptSign). Especially, CLIP is adopted as the visual backbone to extract frame-wise features whose parameters are fixed, and a set of learnable modules are introduced to model spatial sign variations or capture temporal sign movements. The introduced additional modules are quite lightweight, only owning 3.2% extra computations with high efficiency. The generic knowledge acquired in the pretraining stage is well-preserved in the frozen CLIP backbone in this process. Extensive experiments show that despite being efficient, AdaptSign is able to demonstrate superior performance across a series of CSLR benchmarks including PHOENIX14, PHOENIX14-T, CSL-Daily and CSL compared to existing methods. Visualizations show that AdaptSign could learn to dynamically pay major attention to the informative spatial regions and cross-frame trajectories in sign videos.
Visual object tracking plays a critical role in visual-based autonomous systems, as it aims to estimate the position and size of the object of interest within a live video. Despite significant progress made in this field, state-of-the-art (SOTA) trackers often fail when faced with adversarial perturbations in the incoming frames. This can lead to significant robustness and security issues when these trackers are deployed in the real world. To achieve high accuracy on both clean and adversarial data, we propose building a spatial-temporal continuous representation using the semantic text guidance of the object of interest. This novel continuous representation enables us to reconstruct incoming frames to maintain semantic and appearance consistency with the object of interest and its clean counterparts. As a result, our proposed method successfully defends against different SOTA adversarial tracking attacks while maintaining high accuracy on clean data. In particular, our method significantly increases tracking accuracy under adversarial attacks with around 90% relative improvement on UAV123, which is even higher than the accuracy on clean data.
Skeleton-aware sign language recognition (SLR) has gained popularity due to its ability to remain unaffected by background information and its lower computational requirements. Current methods utilize spatial graph modules and temporal modules to capture spatial and temporal features, respectively. However, their spatial graph modules are typically built on fixed graph structures such as graph convolutional networks or a single learnable graph, which only partially explore joint relationships. Additionally, a simple temporal convolution kernel is used to capture temporal information, which may not fully capture the complex movement patterns of different signers. To overcome these limitations, we propose a new spatial architecture consisting of two concurrent branches, which build input-sensitive joint relationships and incorporates specific domain knowledge for recognition, respectively. These two branches are followed by an aggregation process to distinguishe important joint connections. We then propose a new temporal module to model multi-scale temporal information to capture complex human dynamics. Our method achieves state-of-the-art accuracy compared to previous skeleton-aware methods on four large-scale SLR benchmarks. Moreover, our method demonstrates superior accuracy compared to RGB-based methods in most cases while requiring much fewer computational resources, bringing better accuracy-computation trade-off. Code is available at https://github.com/hulianyuyy/DSTA-SLR.
Recent weakly supervised semantic segmentation (WSSS) methods strive to incorporate contextual knowledge to improve the completeness of class activation maps (CAM). In this work, we argue that the knowledge bias between instances and contexts affects the capability of the prototype to sufficiently understand instance semantics. Inspired by prototype learning theory, we propose leveraging prototype awareness to capture diverse and fine-grained feature attributes of instances. The hypothesis is that contextual prototypes might erroneously activate similar and frequently co-occurring object categories due to this knowledge bias. Therefore, we propose to enhance the prototype representation ability by mitigating the bias to better capture spatial coverage in semantic object regions. With this goal, we present a Context Prototype-Aware Learning (CPAL) strategy, which leverages semantic context to enrich instance comprehension. The core of this method is to accurately capture intra-class variations in object features through context-aware prototypes, facilitating the adaptation to the semantic attributes of various instances. We design feature distribution alignment to optimize prototype awareness, aligning instance feature distributions with dense features. In addition, a unified training framework is proposed to combine label-guided classification supervision and prototypes-guided self-supervision. Experimental results on PASCAL VOC 2012 and MS COCO 2014 show that CPAL significantly improves off-the-shelf methods and achieves state-of-the-art performance. The project is available at https://github.com/Barrett-python/CPAL.
In this paper, we study a new problem of cross-domain video based person re-identification (Re-ID). Specifically, we take the synthetic video dataset as the source domain for training and use the real-world videos for testing, which significantly reduces the dependence on real training data collection and annotation. To unveil the power of synthetic data for video person Re-ID, we first propose a self-supervised domain invariant feature learning strategy for both static and temporal features. Then, to further improve the person identification ability in the target domain, we develop a mean-teacher scheme with the self-supervised ID consistency loss. Experimental results on four real datasets verify the rationality of cross-synthetic-real domain adaption and the effectiveness of our method. We are also surprised to find that the synthetic data performs even better than the real data in the cross-domain setting.
Multi-view multi-human association and tracking (MvMHAT), is a new but important problem for multi-person scene video surveillance, aiming to track a group of people over time in each view, as well as to identify the same person across different views at the same time, which is different from previous MOT and multi-camera MOT tasks only considering the over-time human tracking. This way, the videos for MvMHAT require more complex annotations while containing more information for self learning. In this work, we tackle this problem with a self-supervised learning aware end-to-end network. Specifically, we propose to take advantage of the spatial-temporal self-consistency rationale by considering three properties of reflexivity, symmetry and transitivity. Besides the reflexivity property that naturally holds, we design the self-supervised learning losses based on the properties of symmetry and transitivity, for both appearance feature learning and assignment matrix optimization, to associate the multiple humans over time and across views. Furthermore, to promote the research on MvMHAT, we build two new large-scale benchmarks for the network training and testing of different algorithms. Extensive experiments on the proposed benchmarks verify the effectiveness of our method. We have released the benchmark and code to the public.
The sixth-generation (6G) network is expected to provide both communication and sensing (C&S) services. However, spectrum scarcity poses a major challenge to the harmonious coexistence of C&S systems. Without effective cooperation, the interference resulting from spectrum sharing impairs the performance of both systems. This paper addresses C&S interference within a distributed network. Different from traditional schemes that require pilot-based high-frequency interactions between C&S systems, we introduce a third party named the radio map to provide the large-scale channel state information (CSI). With large-scale CSI, we optimize the transmit power of C&S systems to maximize the signal-to-interference-plus-noise ratio (SINR) for the radar detection, while meeting the ergodic rate requirement of the interfered user. Given the non-convexity of both the objective and constraint, we employ the techniques of auxiliary-function-based scaling and fraction programming for simplification. Subsequently, we propose an iterative algorithm to solve this problem. Simulation results collaborate our idea that the extrinsic information, i.e., positions and surroundings, is effective to decouple C&S interference.
The goal of Continual Learning (CL) is to continuously learn from new data streams and accomplish the corresponding tasks. Previously studied CL assumes that data are given in sequence nose-to-tail for different tasks, thus indeed belonging to Serial Continual Learning (SCL). This paper studies the novel paradigm of Parallel Continual Learning (PCL) in dynamic multi-task scenarios, where a diverse set of tasks is encountered at different time points. PCL presents challenges due to the training of an unspecified number of tasks with varying learning progress, leading to the difficulty of guaranteeing effective model updates for all encountered tasks. In our previous conference work, we focused on measuring and reducing the discrepancy among gradients in a multi-objective optimization problem, which, however, may still contain negative transfers in every model update. To address this issue, in the dynamic multi-objective optimization problem, we introduce task-specific elastic factors to adjust the descent direction towards the Pareto front. The proposed method, called Elastic Multi-Gradient Descent (EMGD), ensures that each update follows an appropriate Pareto descent direction, minimizing any negative impact on previously learned tasks. To balance the training between old and new tasks, we also propose a memory editing mechanism guided by the gradient computed using EMGD. This editing process updates the stored data points, reducing interference in the Pareto descent direction from previous tasks. Experiments on public datasets validate the effectiveness of our EMGD in the PCL setting.