MarkIt uses a query-to-mask bridge with open-vocabulary segmentation to add visual markers and frame indices to videos, enabling Vid-LLMs to achieve state-of-the-art temporal grounding on moment retrieval and highlight detection benchmarks.
Tar-tvg: Enhancing vlms with timestamp anchor-constrained reasoning for temporal video grounding
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
TempR1 applies temporal-aware multi-task RL using GRPO and three types of localization rewards to achieve SOTA temporal understanding in MLLMs with synergistic gains from joint optimization.
citing papers explorer
-
MarkIt: Training-Free Visual Markers for Precise Video Temporal Grounding
MarkIt uses a query-to-mask bridge with open-vocabulary segmentation to add visual markers and frame indices to videos, enabling Vid-LLMs to achieve state-of-the-art temporal grounding on moment retrieval and highlight detection benchmarks.
-
TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning
TempR1 applies temporal-aware multi-task RL using GRPO and three types of localization rewards to achieve SOTA temporal understanding in MLLMs with synergistic gains from joint optimization.