activity
20182026
most citedChannel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition

52 citations · 101 across the 21 of their papers we have counts for

collaborators
Showing cs.CVShow all

24 papers · 1 filter

cs.CV2026

Dynamic-Robust Photometric-Semantic Reconstruction for Open-Vocabulary 3D Scene Understanding

Boyu Cai, Li Yang, Yan Xu +6

The integration of novel view synthesis (NVS) and open-vocabulary segmentation (OVS) has recently yielded powerful feed-forward 3D foundation models. However, their inherent relian…

cs.CV2026

Gaussian Mixture Modeling for Event-Aware Visual Allocation in Long Video Understanding

Yifan Lu, Ziqi Zhang, Chunfeng Yuan +3

Large Vision-Language Models (LVLMs) face significant challenges in long video understanding due to the excessive computational cost and information loss associated with uniform sa…

cs.CV2026

MMAgent-R: Learning to Rerank and Reject for Agentic mRAG

Tao Zhang, Ziqi Zhang, Zongyang Ma +7

Knowledge-based Visual Question Answering (KB-VQA) requires models to retrieve visual entities matching the query image from large-scale encyclopedic knowledge bases and answer rel…

cs.CV2026

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings

Zhiheng Li, Zongyang Ma, Jiaxian Chen +12

The past year has seen over 20 open-source document parsing models, yet thefield still benchmarks almost exclusively on OmniDocBench, a 1,355-pagemanually annotated dataset whose t…

cs.CV2026

Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation

Zhiheng Li, Zongyang Ma, Yuntong Pan +8

Multimodal Large Language Models (MLLMs) are increasingly being deployed as automated content moderators. Within this landscape, we uncover a critical threat: Adversarial Smuggling…

cs.CV2026

Beyond Semantic Search: Towards Referential Anchoring in Composed Image Retrieval

Yuxin Yang, Yinan Zhou, Yuxin Chen +6

Composed Image Retrieval (CIR) has demonstrated significant potential by enabling flexible multimodal queries that combine a reference image and modification text. However, CIR inh…