16 citations · 18 across the 7 of their papers we have counts for
7 papers · 1 filter
VISA: Group-wise Visual Token Selection and Aggregation via Graph Summarization for Efficient MLLMs Inference
Pengfei Jiang, Hanjun Li, Linglan Zhao +4
In this study, we introduce a novel method called group-wise \textbf{VI}sual token \textbf{S}election and \textbf{A}ggregation (VISA) to address the issue of inefficient inference…
Multimodal Label Relevance Ranking via Reinforcement Learning
Taian Guo, Taolin Zhang, Haoqian Wu +3
Conventional multi-label recognition methods often focus on label confidence, frequently overlooking the pivotal role of partial order relations consistent with human preference. T…
D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance Annotation
Hanjun Li, Xiujun Shu, Sunan He +5
Temporal sentence grounding (TSG) aims to locate a specific moment from an untrimmed video with a given natural language query. Recently, weakly supervised methods still have a lar…
Unified and Dynamic Graph for Temporal Character Grouping in Long Videos
Xiujun Shu, Wei Wen, Liangsheng Xu +6
Video temporal character grouping locates appearing moments of major characters within a video according to their identities. To this end, recent works have evolved from unsupervis…
Collaborative Noisy Label Cleaner: Learning Scene-aware Trailers for Multi-modal Highlight Detection in Movies
Bei Gan, Xiujun Shu, Ruizhi Qiao +4
Movie highlights stand out of the screenplay for efficient browsing and play a crucial role on social media platforms. Based on existing efforts, this work has two observations: (1…
SIOD: Single Instance Annotated Per Category Per Image for Object Detection
Hanjun Li, Xingjia Pan, Ke Yan +2
Object detection under imperfect data receives great attention recently. Weakly supervised object detection (WSOD) suffers from severe localization issues due to the lack of instan…
Combined Depth Space based Architecture Search For Person Re-identification
Hanjun Li, Gaojie Wu, Wei-Shi Zheng
Most works on person re-identification (ReID) take advantage of large backbone networks such as ResNet, which are designed for image classification instead of ReID, for feature ext…