Research map / Video / Video-language understanding
MEGA: Multimodal Alignment Aggregation and Distillation For Cinematic Video Segmentation
Najmeh Sadoughi, Xinyu Li, Avijit Vajpayee, David Fan, Bing Shuai, Hector Santos-Villalobos, Vimal Bhat, Rohith MV
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 alignment positional encoding (ablation) | MEGA · TRIPOD act segmentation | TA (%): 5.29 -> 13.93 | Improved |
| add alignment positional encoding (ablation) | MEGA · MovieNet-318 scene segmentation | AP (%): 57.77 -> 58.59 | Improved |
| add alignment PE to bottleneck fusion tokens (V+T) (ablation) | MEGA · TRIPOD | TA (%): 13.01 -> 14.63 | Improved |
| use aligned bottleneck fusion instead of late fusion (ablation) | MEGA · TRIPOD act segmentation | TA (%): 12.57 -> 13.93 | Improved |
| use multimodal synchronization with video features instead of screenplay-based synchronization (ablation) | MEGA · TRIPOD act segmentation | TA (%): 10.51 -> 13.93 | Improved |
| add BaSSL features to input (ablation) | MEGA scene segmentation · MovieNet-318 | AP (%): 51.88 -> 58.59 | Improved |
| add CLIP_movie features to input (ablation) | MEGA act segmentation · TRIPOD | TA (%): 6.09 -> 13.93 | Improved |
| add subtitle text features to visual input (ablation) | MEGA act segmentation · TRIPOD | TA (%): 13.93 -> 14.63 | Improved |
| add audio features to MEGA (ablation) | MEGA scene segmentation · MovieNet-318 | AP (%): 58.59 -> 55.36 | Hurt |
| add audio features (acoustic) to T+V act segmentation (ablation) | MEGA · TRIPOD | TA (%): 14.63 -> 14.19 | Hurt |
| use 3 visual modalities instead of single modality (ablation) | MEGA scene segmentation · MovieNet-318 | AP (%) / F1 (%): +0.67 AP, +4.59 F1 | Improved |
| expand GRAPHTP to same feature set Set2 as MEGA (ablation) | GRAPHTP vs MEGA · TRIPOD | TA (%): 4.72 -> 14.19 | Improved |
Closest papers by meaning
- MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation (CVPR 2025 · similarity 0.86)
- Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation (AAAI 2024 · similarity 0.85)
- SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis (CVPR 2025 · similarity 0.85)
- CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generation (NeurIPS 2025 · similarity 0.85)
- VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text Models (CVPR 2025 · similarity 0.85)
- With Limited Data for Multimodal Alignment, Let the STRUCTURE Guide You (NeurIPS 2025 · similarity 0.84)
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.
