TCoT uses a single VLM to select question-relevant video frames from segments, then answers from that curated context, improving video QA accuracy across four benchmarks and three VLMs.
Gpt-4v(ision) system card
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Temporal Chain of Thought: Long-Video Understanding by Thinking in Frames
TCoT uses a single VLM to select question-relevant video frames from segments, then answers from that curated context, improving video QA accuracy across four benchmarks and three VLMs.