2 papers
cs.CV2025
LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detection
Pengcheng Zhao, Zhixian He, Fuwei Zhang +2
Video Moment Retrieval and Highlight Detection aim to find corresponding content in the video based on a text query. Existing models usually first use contrastive learning methods…
cs.CV2024
QTG-VQA: Question-Type-Guided Architectural for VideoQA Systems
Zhixian He, Pengcheng Zhao, Fuwei Zhang +1
In the domain of video question answering (VideoQA), the impact of question types on VQA systems, despite its critical importance, has been relatively under-explored to date. Howev…