A clue-grounded audio-visual counting benchmark over 497 long videos and an RL-trained counting model, whose headline result is undermined by training on the DVD-Counting evaluation benchmark.
Video-llama: An instruction-tuned audio-visual language model for video understanding
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
AV-Reasoner: Improving and Benchmarking Clue-Grounded Audio-Visual Counting for MLLMs
A clue-grounded audio-visual counting benchmark over 497 long videos and an RL-trained counting model, whose headline result is undermined by training on the DVD-Counting evaluation benchmark.