2 papers
cs.CV2025
D2Pruner: Debiased Importance and Structural Diversity for MLLM Token Pruning
Evelyn Zhang, Fufu Yu, Aoqi Wu +5
Processing long visual token sequences poses a significant computational burden on Multimodal Large Language Models (MLLMs). While token pruning offers a path to acceleration, we f…
cs.CV2025
MS-DETR: Towards Effective Video Moment Retrieval and Highlight Detection by Joint Motion-Semantic Learning
Hongxu Ma, Guanshuo Wang, Fufu Yu +2
Video Moment Retrieval (MR) and Highlight Detection (HD) aim to pinpoint specific moments and assess clip-wise relevance based on the text query. While DETR-based joint frameworks…