Research map / Continual learning / Online and replay-based
vCLIMB: A Novel Video Class Incremental Learning Benchmark
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 consistency regularization to iCaRL with 4 frames/video (ablation) | iCaRL on Kinetics · Kinetics, 10 tasks | Acc: 30.73% -> 35.32% | Helped |
| Add temporal consistency regularization to iCaRL with 8 frames/video (ablation) | iCaRL on Kinetics · Kinetics, 10 tasks | Acc: 32.04% -> 36.24% | Helped |
| Add temporal consistency regularization to iCaRL with 16 frames/video (ablation) | iCaRL on Kinetics · Kinetics, 10 tasks | Acc: 31.36% -> 36.54% | Helped |
| Add temporal consistency regularization to iCaRL with 4 frames/video (ablation) | iCaRL on ActivityNet-Trim · ActivityNet-Trim, 10 tasks | Acc: 21.63% -> 42.99% | Helped |
| Add temporal consistency regularization to iCaRL with 8 frames/video (ablation) | iCaRL on ActivityNet-Trim · ActivityNet-Trim, 10 tasks | Acc: 21.54% -> 45.73% | Helped |
| Add temporal consistency regularization to iCaRL with 16 frames/video (ablation) | iCaRL on ActivityNet-Trim · ActivityNet-Trim, 10 tasks | Acc: 25.27% -> 44.04% | Helped |
| Add temporal consistency regularization to iCaRL with 4 frames/video (ablation) | iCaRL on ActivityNet-Untrim · ActivityNet-Untrim, 10 tasks | Acc: 16.28% -> 36.07% | Helped |
| Add temporal consistency regularization to iCaRL with 8 frames/video (ablation) | iCaRL on ActivityNet-Untrim · ActivityNet-Untrim, 10 tasks | Acc: 16.67% -> 40.29% | Helped |
| Add temporal consistency regularization to iCaRL with 16 frames/video (ablation) | iCaRL on ActivityNet-Untrim · ActivityNet-Untrim, 10 tasks | Acc: 21.27% -> 40.45% | Helped |
| Add temporal consistency regularization to iCaRL with 4 frames/video (ablation) | iCaRL on UCF101 · UCF101, 10 tasks | Acc: 80.32% -> 73.85% | Hurt |
| Add temporal consistency regularization to iCaRL with 8 frames/video (ablation) | iCaRL on UCF101 · UCF101, 10 tasks | Acc: 81.12% -> 74.25% | Hurt |
| Add temporal consistency regularization to iCaRL with 16 frames/video (ablation) | iCaRL on UCF101 · UCF101, 10 tasks | Acc: 81.06% -> 75.84% | Hurt |
Closest papers by meaning
- ViLCo-Bench: VIdeo Language COntinual learning Benchmark (NeurIPS 2024 · similarity 0.90)
- Enhancing Visual Continual Learning with Language-Guided Supervision (CVPR 2024 · similarity 0.88)
- Re-evaluating Continual Learning with Few-Shot Adaptation (NeurIPS 2026 · similarity 0.88)
- Bisecle: Binding and Separation in Continual Learning for Video Language Understanding (NeurIPS 2025 · similarity 0.88)
- Continual Learning Using a Kernel-Based Method Over Foundation Models (AAAI 2025 · similarity 0.87)
- Advancing Prompt-Based Methods for Replay-Independent General Continual Learning (ICLR 2025 · similarity 0.87)
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.