Reviso prioritizes key visual evidence in video captioning
Reviso builds CFP observation plans and trains with GRPO to outperform baselines on four benchmarks and improve downstream video question answering.
Stories per day · 30 days
Relatedgrpo2mllm2active-perception1agentic-ai1audiovisual1benchmark1code-generation1event-alignment1multimodal1omni-language-models1sft1
3 stories, newest first · one card per story
Stories tagged #video-captioning
CodeCap-Bench asks whether code captions preserve video content
On 323 structured 2D videos, code captions beat natural language on question answering and reconstruction, but models still miss complex motion.
EVA-Cap: Optimizing Audiovisual Video Captioning via Event-Centric Alignment
EVA-Cap improves audiovisual captions by aligning them to atomic events with SFT and GRPO.