4 papers
SVAG-Bench: A Large-Scale Benchmark for Multi-Instance Spatio-temporal Video Action Grounding
Tanveer Hannan, Shuaicong Wu, Mark Weber +6
A truly capable AI system must do more than detect objects or recognize activities in isolation. It must form unified, grounded representations of who is acting, what they are doin…
EVTP-IVS: Effective Visual Token Pruning For Unifying Instruction Visual Segmentation In Multi-Modal Large Language Models
Wenhui Zhu, Xiwen Chen, Zhipeng Wang +5
Instructed Visual Segmentation (IVS) tasks require segmenting objects in images or videos based on natural language instructions. While recent multimodal large language models (MLL…
Local2Global query Alignment for Video Instance Segmentation
Rajat Koner, Zhipeng Wang, Srinivas Parthasarathy +1
Online video segmentation methods excel at handling long sequences and capturing gradual changes, making them ideal for real-world applications. However, achieving temporally consi…
Perceive, Query & Reason: Enhancing Video QA with Question-Guided Temporal Queries
Roberto Amoroso, Gengyuan Zhang, Rajat Koner +3
Video Question Answering (Video QA) is a challenging video understanding task that requires models to comprehend entire videos, identify the most relevant information based on cont…