Related papers: An Efficient Token Compression Framework for Visua…
Visual object tracking is a fundamental and time-critical vision task. Recent years have seen many shallow tracking methods based on real-time pixel-based correlation filters, as well as deep methods that have top performance but need a…
Image compression is a widely used technique to reduce the spatial redundancy in images. Recently, learning based image compression has achieved significant progress by using the powerful representation ability from neural networks.…
As terminal agents scale to long-horizon, multi-turn workflows, a key bottleneck is not merely limited context length, but the accumulation of noisy terminal observations in the interaction history. Retaining raw observations preserves…
We introduce PRANCE, a Vision Transformer compression framework that jointly optimizes the activated channels and reduces tokens, based on the characteristics of inputs. Specifically, PRANCE~ leverages adaptive token optimization strategies…
We propose an object tracking method, SFTrack++, that smoothly learns to preserve the tracked object consistency over space and time dimensions by taking a spectral clustering approach over the graph of pixels from the video, using a fast…
Discrminative trackers, employ a classification approach to separate the target from its background. To cope with variations of the target shape and appearance, the classifier is updated online with different samples of the target and the…
This paper investigates the fundamental relationship between model capacity and the minimal number of visual tokens required to preserve image semantics. Inspired by the Minimum Description Length principle, we reinterpret image tokens as…
Tissue tracking plays a critical role in various surgical navigation and extended reality (XR) applications. While current methods trained on large synthetic datasets achieve high tracking accuracy and generalize well to endoscopic scenes,…
How to make a good trade-off between performance and computational cost is crucial for a tracker. However, current famous methods typically focus on complicated and time-consuming learning that combining temporal and appearance information…
Point tracking aims to localize corresponding points across video frames, serving as a fundamental task for 4D reconstruction, robotics, and video editing. Existing methods commonly rely on shallow convolutional backbones such as ResNet…
Multi-Object Tracking (MOT) is a critical problem in computer vision, essential for understanding how objects move and interact in videos. This field faces significant challenges such as occlusions and complex environmental dynamics,…
The $\ell_1$ tracker obtains robustness by seeking a sparse representation of the tracking object via $\ell_1$ norm minimization \cite{Xue_ICCV_09_Track}. However, the high computational complexity involved in the $ \ell_1 $ tracker…
Tokenization in video models, typically through patchification, generates an excessive and redundant number of tokens. This severely limits video efficiency and scalability. While recent trajectory-based tokenizers offer a promising…
Deep networks have been successfully applied to visual tracking by learning a generic representation offline from numerous training images. However the offline training is time-consuming and the learned generic representation may be less…
Deep learning based visual trackers entail offline pre-training on large volumes of video datasets with accurate bounding box annotations that are labor-expensive to achieve. We present a new framework to facilitate bounding box annotations…
We propose ProTracker, a novel framework for accurate and robust long-term dense tracking of arbitrary points in videos. Previous methods relying on global cost volumes effectively handle large occlusions and scene changes but lack…
Compared with previous two-stream trackers, the recent one-stream tracking pipeline, which allows earlier interaction between the template and search region, has achieved a remarkable performance gain. However, existing one-stream trackers…
Single-stream architectures using Vision Transformer (ViT) backbones show great potential for real-time UAV tracking recently. However, frequent occlusions from obstacles like buildings and trees expose a major drawback: these models often…
The tracking-by-detection framework usually consist of two stages: drawing samples around the target object in the first stage and classifying each sample as the target object or background in the second stage. Current popular trackers…
The unique complementarity of frame-based and event cameras for high frame rate object tracking has recently inspired some research attempts to develop multi-modal fusion approaches. However, these methods directly fuse both modalities and…