Related papers: GateMOT: Q-Gated Attention for Dense Object Tracki…
Quantization-aware training (QAT) has achieved remarkable success in low-bit ($\leq$4-bit) quantization for classification networks. However, when applied to more complex visual tasks such as object detection and image segmentation,…
Object-based attention is a key component of the visual system, relevant for perception, learning, and memory. Neurons tuned to features of attended objects tend to be more active than those associated with non-attended objects. There is a…
The success of self-attention lies in its ability to capture long-range dependencies and enhance context understanding, but it is limited by its computational complexity and challenges in handling sequential data with inherent…
Self-attention has greatly contributed to the success of the widely used Transformer architecture by enabling learning from data with long-range dependencies. In an effort to improve performance, a gated attention model that leverages a…
Although attention-based Neural Machine Translation (NMT) has achieved remarkable progress in recent years, it still suffers from issues of repeating and dropping translations. To alleviate these issues, we propose a novel key-value…
Attention mechanism has been extensively integrated within mainstream neural network architectures, such as Transformers and graph attention networks. Yet, its underlying working principles remain somewhat elusive. What is its essence? Are…
The rapid growth of Internet services and mobile devices provides an excellent opportunity to satisfy the strong demand for the personalized item or product recommendation. However, with the tremendous increase of users and items,…
Multi-person pose tracking is an important element for many applications and requires to estimate the human poses of all persons in a video and to track them over time. The association of poses across frames remains an open research…
Multi-object tracking (MOT) has profound applications in a variety of fields, including surveillance, sports analytics, self-driving, and cooperative robotics. Despite considerable advancements, existing MOT methodologies tend to falter…
Modern autoregressive models rely on attention, yet the Softmax full attention in Transformers scales quadratically with sequence length. Sliding Window Attention (SWA) achieves linear-time encoding/decoding by constraining the attention…
Visual attention mechanisms are a key component of neural network models for computer vision. By focusing on a discrete set of objects or image regions, these mechanisms identify the most relevant features and use them to build more…
Can a transformer learn which attention entries matter during training? In principle, yes: attention distributions are highly concentrated, and a small gate network can identify the important entries post-hoc with near-perfect accuracy. In…
Multi-object tracking (MOT) is an important problem in computer vision which has a wide range of applications. Formulating MOT as multi-task learning of object detection and re-ID in a single network is appealing since it allows joint…
Transformers have achieved widespread and remarkable success, while the computational complexity of their attention modules remains a major bottleneck for vision tasks. Existing methods mainly employ 8-bit or 4-bit quantization to balance…
Long video understanding remains a formidable challenge for Multimodal Large Language Models (MLLMs) due to the prohibitive computational cost of processing dense frame sequences. Prevailing solutions, which select a keyframe subset,…
Dense object tracking, the ability to localize specific object points with pixel-level accuracy, is an important computer vision task with numerous downstream applications in robotics. Existing approaches either compute dense keypoint…
Attention is the cornerstone of modern Large Language Models (LLMs). Yet its quadratic complexity hinders efficiency and scalability, especially for long-context processing. A promising approach is to leverage sparsity in attention.…
Multi-object tracking (MOT) is a fundamental problem in computer vision with numerous applications, such as intelligent surveillance and automated driving. Despite the significant progress made in MOT, pedestrian attributes, such as gender,…
The transformer architecture predominates across various models. As the heart of the transformer, attention has a computational complexity of $O(N^2)$, compared to $O(N)$ for linear transformations. When handling large sequence lengths,…
Large language model (LLM) inference demands significant amount of computation and memory, especially in the key attention mechanism. While techniques, such as quantization and acceleration algorithms, like FlashAttention, have improved…