Related papers: Target-Aware Tracking with Long-term Context Atten…
Long-context language modeling is commonly framed as a scalability challenge of token-level attention, yet local-to-global information structuring remains largely implicit in existing approaches. Drawing on cognitive theories of discourse…
Block-wise sparse attention offers significant efficiency gains for long-context modeling, yet existing methods often suffer from low selection fidelity and cumulative contextual loss by completely discarding unselected blocks. To address…
Existing Visual Object Tracking (VOT) only takes the target area in the first frame as a template. This causes tracking to inevitably fail in fast-changing and crowded scenes, as it cannot account for changes in object appearance between…
The timeline of computer vision research is marked with advances in learning and utilizing efficient contextual representations. Most of them, however, are targeted at improving model performance on a single downstream task. We consider a…
A long-term visual object tracking performance evaluation methodology and a benchmark are proposed. Performance measures are designed by following a long-term tracking definition to maximize the analysis probing strength. The new measures…
Long contexts improve capabilities of large language models but pose serious hardware challenges: compute and memory footprints grow linearly with sequence length. Particularly, the decoding phase continuously accesses massive KV cache,…
Transformer networks have achieved remarkable success across diverse domains, leveraging a variety of architectural innovations, including residual connections. However, traditional residual connections, which simply sum the outputs of…
Although transformer architectures have achieved state-of-the-art performance across diverse domains, their quadratic computational complexity with respect to sequence length remains a significant bottleneck, particularly for…
The challenging task of multi-object tracking (MOT) requires simultaneous reasoning about track initialization, identity, and spatio-temporal trajectories. We formulate this task as a frame-to-frame set prediction problem and introduce…
Transformer-based trackers have achieved promising success and become the dominant tracking paradigm due to their accuracy and efficiency. Despite the substantial progress, most of the existing approaches tackle object tracking as a…
Recent advances in video generation can produce realistic, minute-long single-shot videos with scalable diffusion transformers. However, real-world narrative videos require multi-shot scenes with visual and dynamic consistency across shots.…
The ability of Large Language Models (LLMs) to process and generate coherent text is markedly weakened when the number of input tokens exceeds their pretraining length. Given the expensive overhead of finetuning large-scale models with…
This paper introduces a novel approach to enhance the capabilities of Large Language Models (LLMs) in processing and understanding extensive text sequences, a critical aspect in applications requiring deep comprehension and synthesis of…
We propose a light-weight and highly efficient Joint Detection and Tracking pipeline for the task of Multi-Object Tracking using a fully-transformer architecture. It is a modified version of TransTrack, which overcomes the computational…
Accurate tracking is still a challenging task due to appearance variations, pose and view changes, and geometric deformations of target in videos. Recent anchor-free trackers provide an efficient regression mechanism but fail to produce…
In the realm of unmanned aerial vehicle (UAV) tracking, Siamese-based approaches have gained traction due to their optimal balance between efficiency and precision. However, UAV scenarios often present challenges such as insufficient…
Object tracking quality usually depends on video context (e.g. object occlusion level, object density). In order to decrease this dependency, this paper presents a learning approach to adapt the tracker parameters to the context variations.…
Template-matching methods for visual tracking have gained popularity recently due to their good performance and fast speed. However, they lack effective ways to adapt to changes in the target object's appearance, making their tracking…
In recent years, target tracking has made great progress in accuracy. This development is mainly attributed to powerful networks (such as transformers) and additional modules (such as online update and refinement modules). However, less…
Most current multi-object trackers focus on short-term tracking, and are based on deep and complex systems that often cannot operate in real-time, making them impractical for video-surveillance. In this paper we present a long-term,…