10 papers
RotVLA: Rotational Latent Action for Vision-Language-Action Model
Qiwei Li, Xicheng Gong, Xinghang Li +5
Latent Action Models (LAMs) have emerged as an effective paradigm for handling heterogeneous datasets during Vision-Language-Action (VLA) model pretraining, offering a unified acti…
RS-SSM: Refining Forgotten Specifics in State Space Model for Video Semantic Segmentation
Kai Zhu, Zhenyu Cui, Zehua Zang +1
Recently, state space models have demonstrated efficient video segmentation through linear-complexity state space compression. However, Video Semantic Segmentation (VSS) requires p…
Bi-C2R: Bidirectional Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification
Zhenyu Cui, Jiahuan Zhou, Yuxin Peng
Lifelong person Re-IDentification (L-ReID) exploits sequentially collected data to continuously train and update a ReID model, focusing on the overall performance of all data. Its…
CKDA: Cross-modality Knowledge Disentanglement and Alignment for Visible-Infrared Lifelong Person Re-identification
Zhenyu Cui, Jiahuan Zhou, Yuxin Peng
Lifelong person Re-IDentification (LReID) aims to match the same person employing continuously collected individual data from different scenarios. To achieve continuous all-day per…
UPP: Unified Point-Level Prompting for Robust Point Cloud Analysis
Zixiang Ai, Zhenyu Cui, Yuxin Peng +1
Pre-trained point cloud analysis models have shown promising advancements in various downstream tasks, yet their effectiveness is typically suffering from low-quality point cloud (…
STOP: Integrated Spatial-Temporal Dynamic Prompting for Video Understanding
Zichen Liu, Kunlun Xu, Bing Su +3
Pre-trained on tremendous image-text pairs, vision-language models like CLIP have demonstrated promising zero-shot generalization across numerous image-based tasks. However, extend…