MUSEG applies timestamp-aware multi-segment grounding with a phased-reward RL recipe to boost temporal grounding and time-sensitive video QA performance in MLLMs.
Online video understanding: A comprehensive benchmark and memory-augmented method
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 5verdicts
UNVERDICTED 5roles
baseline 1polarities
baseline 1representative citing papers
VideoChat-Flash applies hierarchical video token compression to achieve ~50x reduction in context length for long videos while maintaining near-original performance on long-context benchmarks.
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.
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.
Seed1.5-VL is a compact multimodal model that sets new records on dozens of vision-language benchmarks and outperforms prior systems on agent-style tasks.
citing papers explorer
-
MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding
MUSEG applies timestamp-aware multi-segment grounding with a phased-reward RL recipe to boost temporal grounding and time-sensitive video QA performance in MLLMs.
-
VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling
VideoChat-Flash applies hierarchical video token compression to achieve ~50x reduction in context length for long videos while maintaining near-original performance on long-context 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.
-
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.
-
Seed1.5-VL Technical Report
Seed1.5-VL is a compact multimodal model that sets new records on dozens of vision-language benchmarks and outperforms prior systems on agent-style tasks.