Et bench: Towards open-ended event-level video-language understanding
Recent advances in Video Large Language Models (Video-LLMs) have demonstrated their
great potential in general-purpose video understanding. To verify the significance of these …
great potential in general-purpose video understanding. To verify the significance of these …
Saliency-guided detr for moment retrieval and highlight detection
A Gordeev, V Dokholyan, I Tolstykh… - arXiv preprint arXiv …, 2024 - arxiv.org
Existing approaches for video moment retrieval and highlight detection are not able to align
text and video features efficiently, resulting in unsatisfying performance and limited …
text and video features efficiently, resulting in unsatisfying performance and limited …
FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding
Text-guided Video Temporal Grounding (VTG) aims to localize relevant segments in
untrimmed videos based on textual descriptions, encompassing two subtasks: Moment …
untrimmed videos based on textual descriptions, encompassing two subtasks: Moment …
VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrieval
Video Highlight Detection and Moment Retrieval (HD/MR) are essential in video analysis.
Recent joint prediction transformer models often overlook their cross-task dynamics and …
Recent joint prediction transformer models often overlook their cross-task dynamics and …
LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detection
P Zhao, Z He, F Zhang, S Lin, F Zhou - arXiv preprint arXiv:2501.10787, 2025 - arxiv.org
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 …
video based on a text query. Existing models usually first use contrastive learning methods …
Length-Aware DETR for Robust Moment Retrieval
Video Moment Retrieval (MR) aims to localize moments within a video based on a given
natural language query. Given the prevalent use of platforms like YouTube for information …
natural language query. Given the prevalent use of platforms like YouTube for information …
D&M: Enriching E-commerce Videos with Sound Effects by Key Moment Detection and SFX Matching
J Liu, M Wang, Y Ma, B Wang, A Chen, Q Chen… - arXiv preprint arXiv …, 2024 - arxiv.org
Videos showcasing specific products are increasingly important for E-commerce. Key
moments naturally exist as the first appearance of a specific product, presentation of its …
moments naturally exist as the first appearance of a specific product, presentation of its …
: Exploring Embodied Emotion Through A Large-Scale Egocentric Video Dataset
Understanding human emotions is fundamental to enhancing human-computer interaction,
especially for embodied agents that mimic human behavior. Traditional emotion analysis …
especially for embodied agents that mimic human behavior. Traditional emotion analysis …