Research map / Video / Video segmentation and tracking
Seeing Conversations: Communication Context Identification in Egocentric Video
Tobias Dorszewski, Jens Hjortkjær
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 |
|---|---|---|---|
| add temporal LSTM modeling (ablation) | CoCoNet · CCI dataset, combined test | balanced accuracy (%): 83 -> 96 | Improved |
| add inter-person self-attention (ablation) | CoCoNet · CCI dataset, combined test | balanced accuracy (%): 92 -> 96 | Improved |
| add both temporal and interaction modules (ablation) | CoCoNet · CCI dataset, combined test | balanced accuracy (%): 74 -> 96 | Improved |
| combine head direction with face box features (ablation) | CoCoNet · CCI dataset, combined test | balanced accuracy (%): 86 (Fbox), 89 (Fdir) -> 94 | Improved |
| add detection quality and facial landmarks (ablation) | CoCoNet · CCI dataset, combined test | balanced accuracy (%): 94 -> 96 | Improved |
| add ResNet features to the structured feature set (ablation) | CoCoNet · CCI dataset, combined test | balanced accuracy (%): 96 -> 96 | No clear effect |
| train with variable segment lengths instead of fixed 4096 frames (ablation) | CoCoNet · CCI dataset, combined test | TbAcc (%): 79 -> 87 | Improved |
| randomly vary person dimension in training instead of fixed 9 (ablation) | CoCoNet · CCI dataset, combined test | balanced accuracy (%): 92 -> 96 | Improved |
| train only on small groups (2-3) and test on large groups (ablation) | CoCoNet · CCI dataset, group size 6-10 | balanced accuracy (%): 97 -> 27 | Hurt |
| use CoCoNet with self-attention instead of affinity predictor | CoCoNet · CCI dataset, combined test | balanced accuracy (%): 90 -> 94 (same features) | Improved |
| longer temporal context at inference for large groups (ablation) | CoCoNet · CCI dataset, group size 6-10 | balanced accuracy (%): 70 -> 97 | Improved |
| matched versus unseen individuals at test time | CoCoNet · CCI dataset | balanced accuracy (%): 95 -> 97 | No clear effect |
Closest papers by meaning
- The Audio-Visual Conversational Graph: From an Egocentric-Exocentric Perspective (CVPR 2024 · similarity 0.90)
- ANNEXE: Unified Analyzing, Answering, and Pixel Grounding for Egocentric Interaction (CVPR 2025 · similarity 0.86)
- EgoLife: Towards Egocentric Life Assistant (CVPR 2025 · similarity 0.85)
- Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos (CVPR 2025 · similarity 0.85)
- EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views (NeurIPS 2024 · similarity 0.85)
- EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT (NeurIPS 2025 · similarity 0.85)
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.
