7 papers
ForeSea: AI Forensic Search with Multi-modal Queries for Video Surveillance
Hyojin Park, Yi Li, Janghoon Cho +8
Despite decades of work, surveillance still struggles in searching and reasoning about specific targets across long, multi-camera videos. Existing methods - tracking, retrieval, an…
Conditional Multi-Event Temporal Grounding in Long-Form Video
Yuanhao Zou, Arthad Kulkarni, Lucas Tonanez +12
Multimodal large language models have made rapid progress in video temporal grounding, yet real-world applications routinely require localizing every event that satisfies compositi…
Beyond Layer Importance in Layer-wise Sparsity: An Inter-Layer Perturbation-Absorption Perspective
Tao Jing, Ningxin Wu, Chen Kang +3
The considerable layer-wise redundancy in large language models (LLMs) has established non-uniform sparsity allocation across layers as the standard pruning approach for efficient…
Latent Bridge: Feature Delta Prediction for Efficient Dual-System Vision-Language-Action Model Inference
Yudong Liu, Yuan Li, Zijia Tang +12
Dual-system Vision-Language-Action (VLA) models achieve state-of-the-art robotic manipulation but are bottlenecked by the VLM backbone, which must execute at every control step whi…
PSI: A Benchmark for Human Interpretation and Response in Traffic Interactions
Taotao Jing, Tina Chen, Renran Tian +5
Accurately modeling pedestrian intention and understanding driver decision-making processes are critical for the development of safe and socially aware autonomous driving systems.…
DiSa: Saliency-Aware Foreground-Background Disentangled Framework for Open-Vocabulary Semantic Segmentation
Zhen Yao, Xin Li, Taotao Jing +2
Open-vocabulary semantic segmentation aims to assign labels to every pixel in an image based on text labels. Existing approaches typically utilize vision-language models (VLMs), su…