Reinforcement fine-tuning with temporal rewards produces VideoChat-R1, a video MLLM showing large gains on spatio-temporal perception benchmarks such as +31.8 temporal grounding and +31.2 object tracking.
Flashvtg: Feature layering and adaptive score handling network for video temporal grounding
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
ClipTBP adds clip-level alignment loss and dual boundary losses to existing moment retrieval models for more accurate and robust temporal boundary prediction.
citing papers explorer
-
VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning
Reinforcement fine-tuning with temporal rewards produces VideoChat-R1, a video MLLM showing large gains on spatio-temporal perception benchmarks such as +31.8 temporal grounding and +31.2 object tracking.
-
ClipTBP: Clip-Pair based Temporal Boundary Prediction with Boundary-Aware Learning for Moment Retrieval
ClipTBP adds clip-level alignment loss and dual boundary losses to existing moment retrieval models for more accurate and robust temporal boundary prediction.