Related papers: An Efficient Token Compression Framework for Visua…
Conventional multi-object tracking (MOT) systems are predominantly designed for pedestrian tracking and often exhibit limited generalization to other object categories. This paper presents a generalized tracking framework capable of…
Many Multi-Object Tracking (MOT) approaches exploit motion information to associate all the detected objects across frames. However, many methods that rely on filtering-based algorithms, such as the Kalman Filter, often work well in linear…
Recent Vision-Language Models (VLMs) have demonstrated remarkable multimodal understanding capabilities, yet the redundant visual tokens incur prohibitive computational overhead and degrade inference efficiency. Prior studies typically…
Template-based discriminative trackers are currently the dominant tracking methods due to their robustness and accuracy, and the Siamese-network-based methods that depend on cross-correlation operation between features extracted from…
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…
Recent efforts to accelerate inference in Multimodal Large Language Models (MLLMs) have largely focused on visual token compression. The effectiveness of these methods is commonly evaluated by measuring the accuracy drop on existing MLLM…
Accurate and efficient discrete video tokenization is essential for long video sequences processing. Yet, the inherent complexity and variable information density of videos present a significant bottleneck for current tokenizers, which…
Inference speed and tracking performance are two critical evaluation metrics in the field of visual tracking. However, high-performance trackers often suffer from slow processing speeds, making them impractical for deployment on…
Visual text compression (VTC) promises efficient long-context processing by rendering text into an image and re-encoding it with a vision-language model, often producing $3$--$20\times$ fewer decoder tokens than subword tokenization. Yet…
3D single object tracking plays an essential role in many applications, such as autonomous driving. It remains a challenging problem due to the large appearance variation and the sparsity of points caused by occlusion and limited sensor…
Many state-of-the-art trackers usually resort to the pretrained convolutional neural network (CNN) model for correlation filtering, in which deep features could usually be redundant, noisy and less discriminative for some certain instances,…
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…
We propose a novel meta-learning framework for real-time object tracking with efficient model adaptation and channel pruning. Given an object tracker, our framework learns to fine-tune its model parameters in only a few iterations of…
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…
Token compression is essential for reducing the computational and memory requirements of transformer models, enabling their deployment in resource-constrained environments. In this work, we propose an efficient and hardware-compatible token…
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…
Variations of target appearance such as deformations, illumination variance, occlusion, etc., are the major challenges of visual object tracking that negatively impact the performance of a tracker. An effective method to tackle these…
Existing vision tokenization isolates the optimization of vision tokenizers from downstream training, implicitly assuming the visual tokens can generalize well across various tasks, e.g., image generation and visual question answering. The…
Recent advances in transformer-based lightweight object tracking have established new standards across benchmarks, leveraging the global receptive field and powerful feature extraction capabilities of attention mechanisms. Despite these…
RGB-T tracking leverages the complementary strengths of RGB and thermal infrared (TIR) modalities to address challenging scenarios such as low illumination and adverse weather. However, existing methods often fail to effectively integrate…