Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
VidLBEval: Benchmarking and Mitigating Language Bias in Video-Involved LVLMs
Yiming Yang, Yangyang Guo, Hui Lu +1
Recently, Large Vision-Language Models (LVLMs) have made significant strides across diverse multimodal tasks and benchmarks. This paper reveals a largely under-explored problem fro…
cs.CV2024
Efficient Temporal Sentence Grounding in Videos with Multi-Teacher Knowledge Distillation
Renjie Liang, Yiming Yang, Hui Lu +1
Temporal Sentence Grounding in Videos (TSGV) aims to detect the event timestamps described by the natural language query from untrimmed videos. This paper discusses the challenge o…