3 citations · 9 across the 12 of their papers we have counts for
12 papers · 1 filter
Render to Reason: Novel-View Semantic Prediction Improves Spatial Understanding in VLMs
Yuqun Wu, Yao Xiao, Chuhang Zou +2
Recent works augment Vision-Language Models with geometry features from pretrained 3D models, expecting that the geometric signal will boost spatial reasoning. However, we find tha…
SAM-V: Geometry-Aware Segment Anything for Multi-View Instance Segmentation
Jiangshan Gong, Yuqun Wu, Qiqian Fu +4
Consistent multi-view object segmentation is critical for 3D perception and robotics, yet remains challenging under severe viewpoint and occlusion changes. Existing methods typical…
ReToken: Improving Long-Context VLMs with Visual Retrieval Token
Yao Xiao, Reuben Tan, Zhen Zhu +3
Long visual contexts challenge vision-language models: performance degrades as the number of distractors grows, and processing all tokens at once can exceed GPU memory limits. We p…
All-in-One Video Restoration under Smoothly Evolving Unknown Weather Degradations
Wenrui Li, Hongtao Chen, Yao Xiao +4
All-in-one image restoration aims to recover clean images from diverse unknown degradations using a single model. But extending this task to videos faces unique challenges. Existin…
Sparse Reasoning is Enough: Biological-Inspired Framework for Video Anomaly Detection with Large Pre-trained Models
He Huang, Zixuan Hu, Dongxiao Li +2
Video anomaly detection (VAD) plays a vital role in real-world applications such as security surveillance, autonomous driving, and industrial monitoring. Recent advances in large p…
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models
Yao Xiao, Qiqian Fu, Heyi Tao +3
Image-text models excel at image-level tasks but struggle with detailed visual understanding. While these models provide strong visual-language alignment, segmentation models like…
Region-Based Representations Revisited
Michal Shlapentokh-Rothman, Ansel Blume, Yao Xiao +7
We investigate whether region-based representations are effective for recognition. Regions were once a mainstay in recognition approaches, but pixel and patch-based features are no…
Continual Learning in Open-vocabulary Classification with Complementary Memory Systems
Zhen Zhu, Weijie Lyu, Yao Xiao +1
We introduce a method for flexible and efficient continual learning in open-vocabulary image classification, drawing inspiration from the complementary learning systems observed in…
Contributions of Shape, Texture, and Color in Visual Recognition
Yunhao Ge, Yao Xiao, Zhi Xu +2
We investigate the contributions of three important features of the human visual system (HVS)~ -- ~shape, texture, and color ~ -- ~to object classification. We build a humanoid vis…
PatchZero: Defending against Adversarial Patch Attacks by Detecting and Zeroing the Patch
Ke Xu, Yao Xiao, Zhaoheng Zheng +2
Adversarial patch attacks mislead neural networks by injecting adversarial pixels within a local region. Patch attacks can be highly effective in a variety of tasks and physically…
Encouraging Disentangled and Convex Representation with Controllable Interpolation Regularization
Yunhao Ge, Zhi Xu, Yao Xiao +3
We focus on controllable disentangled representation learning (C-Dis-RL), where users can control the partition of the disentangled latent space to factorize dataset attributes (co…
A Peek Into the Reasoning of Neural Networks: Interpreting with Structural Visual Concepts
Yunhao Ge, Yao Xiao, Zhi Xu +5
Despite substantial progress in applying neural networks (NN) to a wide variety of areas, they still largely suffer from a lack of transparency and interpretability. While recent d…