Research map / Video / Video-language understanding
LiveBot: Generating Live Video Comments Based on Visual and Textual Contexts
Shuming Ma, Lei Cui, Damai Dai, Furu Wei, Xu Sun
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use the Unified Transformer instead of S2S-IC | LiveBot · Live Comment Dataset test, video and comments | MRR: 0.2454 -> 0.2753 | Improved |
| Use the Fusional RNN instead of S2S-IC | LiveBot · Live Comment Dataset test, video and comments | MRR: 0.2454 -> 0.2710 | Improved |
| Use the Unified Transformer instead of S2S-IC | LiveBot · Live Comment Dataset test, video and comments | Relevance: 2.23 -> 3.07 | Improved |
| Use the Unified Transformer instead of S2S-IC | LiveBot · Live Comment Dataset test, video and comments | Correctness: 2.91 -> 3.45 | Improved |
| Use the Fusional RNN instead of S2S-IC | LiveBot · Live Comment Dataset test, video and comments | Fluency: 4.07 -> 4.45 | Improved |
| Provide both video frames and surrounding comments instead of video alone | LiveBot · Live Comment Dataset test | MRR: 0.2311 -> 0.2753 | Improved |
| Provide both video frames and surrounding comments instead of comments alone | LiveBot · Live Comment Dataset test | MRR: 0.2513 -> 0.2753 | Improved |
| Use surrounding comments rather than video frames as the sole input | LiveBot · Live Comment Dataset test | MRR: 0.2311 -> 0.2513 | Improved |
| Use the Unified Transformer instead of the Fusional RNN | LiveBot · Live Comment Dataset test, video and comments | Fluency: 4.45 -> 4.31 | Hurt |
Closest papers by meaning
- Enhancing Multimodal Affective Analysis with Learned Live Comment Features (AAAI 2025 · similarity 0.85)
- VideoLLM-online: Online Video Large Language Model for Streaming Video (CVPR 2024 · similarity 0.84)
- LiveStar: Live Streaming Assistant for Real-World Online Video Understanding (NeurIPS 2025 · similarity 0.84)
- VideoAutoArena: An Automated Arena for Evaluating Large Multimodal Models in Video Analysis through User Simulation (CVPR 2025 · similarity 0.82)
- Online Video Understanding: OVBench and VideoChat-Online (CVPR 2025 · similarity 0.82)
- LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale (CVPR 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
