6 papers
Putting Captions to the Test: Evaluating Video Caption Quality through Multiple-Choice Question Answering
Zizhen Wang, Bo Feng, Zhengfeng Lai +5
Evaluating video captioning remains a critical challenge for Visual Large Language Models (VLLMs). Existing metrics primarily rely on matching generated text against ground-truth r…
Evolving Beyond Snapshots: Harmonizing Structure and Sequence via Entity State Tuning for Temporal Knowledge Graph Forecasting
Siyuan Li, Yunjia Wu, Yiyong Xiao +5
Temporal knowledge graph (TKG) forecasting requires predicting future facts by jointly modeling structural dependencies within each snapshot and temporal evolution across snapshots…
A Unified Multi-Agent Framework for Universal Multimodal Understanding and Generation
Jiulin Li, Ping Huang, Yexin Li +3
Real-world multimodal applications often require any-to-any capabilities, enabling both understanding and generation across modalities including text, image, audio, and video. Howe…
Breaking Down Video LLM Benchmarks: Knowledge, Spatial Perception, or True Temporal Understanding?
Bo Feng, Zhengfeng Lai, Shiyu Li +4
Existing video understanding benchmarks often conflate knowledge-based and purely image-based questions, rather than clearly isolating a model's temporal reasoning ability, which i…
StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant
Haibo Wang, Bo Feng, Zhengfeng Lai +6
We present StreamBridge, a simple yet effective framework that seamlessly transforms offline Video-LLMs into streaming-capable models. It addresses two fundamental challenges in ad…
RankUp: Boosting Semi-Supervised Regression with an Auxiliary Ranking Classifier
Pin-Yen Huang, Szu-Wei Fu, Yu Tsao
State-of-the-art (SOTA) semi-supervised learning techniques, such as FixMatch and it's variants, have demonstrated impressive performance in classification tasks. However, these me…