most citedEnd-to-End Human Instance Matting

6 citations · 12 across the 5 of their papers we have counts for

collaborators

5 papers

cs.CV20243 cited

Autoregressive Queries for Adaptive Tracking with Spatio-TemporalTransformers

Jinxia Xie, Bineng Zhong, Zhiyi Mo +4

The rich spatio-temporal information is crucial to capture the complicated target appearance variations in visual tracking. However, most top-performing tracking algorithms rely on…

cs.CV20246 cited

End-to-End Human Instance Matting

Qinglin Liu, Shengping Zhang, Quanling Meng +3

Human instance matting aims to estimate an alpha matte for each human instance in an image, which is extremely challenging and has rarely been studied so far. Despite some efforts…

cs.CV20241 cited

Explicit Visual Prompts for Visual Object Tracking

Liangtao Shi, Bineng Zhong, Qihua Liang +3

How to effectively exploit spatio-temporal information is crucial to capture target appearance changes in visual tracking. However, most deep learning-based trackers mainly focus o…

cs.CV2024

ODTrack: Online Dense Temporal Token Learning for Visual Tracking

Yaozong Zheng, Bineng Zhong, Qihua Liang +3

Online contextual reasoning and association across consecutive video frames are critical to perceive instances in visual tracking. However, most current top-performing trackers per…

cs.CV20232 cited

Towards Unified Token Learning for Vision-Language Tracking

Yaozong Zheng, Bineng Zhong, Qihua Liang +3

In this paper, we present a simple, flexible and effective vision-language (VL) tracking pipeline, termed \textbf{MMTrack}, which casts VL tracking as a token generation task. Trad…