Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/iPerceive (Chadha et al., 2020)

iPerceive (Chadha et al., 2020)

Reported on 7 benchmarks across 3 tasks · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision6 results

Video CaptioningonActivityNet Captions
BLEU-3· 2020-11-16
2.93
best: 17.43 (COOT (ae-test split) - Only Appearance features)
iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering arXiv:2011.07735
Video CaptioningonActivityNet Captions
BLEU-4· 2020-11-16
1.29
best: 9.45 (ADV-INF + Global)
iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering arXiv:2011.07735
Video CaptioningonActivityNet Captions
METEOR· 2020-11-16
7.87
best: 17.97 (VLTinT (ae-test split) C3D/Ling)
iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering arXiv:2011.07735
Dense Video CaptioningonActivityNet Captions
BLEU-3· 2020-11-16
2.93
best: 4.16 (TSP)
iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering arXiv:2011.07735
Dense Video CaptioningonActivityNet Captions
BLEU-4· 2020-11-16
1.29
best: 9.45 (ADV-INF + Global)
iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering arXiv:2011.07735
Dense Video CaptioningonActivityNet Captions
METEOR· 2020-11-16
7.87
best: 17 (Vid2Seq)
iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering arXiv:2011.07735

Reasoning1 result

Video Question AnsweringonTVQA
Accuracy· 2020-11-16
76.96
best: 82.2 (LLaMA-VQA)
SOTA
iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering arXiv:2011.07735