Overview of Tencent Multi-modal Ads Video Understanding Challenge
Not on the map. Why?
Abstract (arXiv)
Multi-modal Ads Video Understanding Challenge is the first grand challenge aiming to comprehensively understand ads videos. Our challenge includes two tasks: video structuring in the temporal dimension and multi-modal video classification. It asks the participants to accurately predict both the scene boundaries and the multi-label categories of each scene based on a fine-grained and ads-related category hierarchy. Therefore, our task has four distinguishing features from previous ones: ads domain, multi-modal information, temporal segmentation, and multi-label classification. It will advance the foundation of ads video understanding and have a significant impact on many ads applications like video recommendation. This paper presents an overview of our challenge, including the background of ads videos, an elaborate description of task and dataset, evaluation protocol, and our proposed baseline. By ablating the key components of our baseline, we would like to reveal the main challenges of this task and provide useful guidance for future research of this area. In this paper, we give an extended version of our challenge overview. The dataset will be publicly available at https://algo.qq.com/.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 40 of its 57 references that are in the map. First posted on arXiv 16 Sep 2021.
Builds on
40 of 57 references.
References · 40
- 2017Attention Is All You Needcited by 59,932
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
- 2017Squeeze-and-Excitation Networkscited by 4,763
- 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
- 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
- 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
- 2021Video Swin Transformercited by 1,090
- 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,067
- 2016Temporal Segment Networks: Towards Good Practices for Deep Action Recognitioncited by 899
28 more
- 2021Multiscale Vision Transformerscited by 896
- 2018Scaling Egocentric Vision: The EPIC-KITCHENS Datasetcited by 789
- 2017Focal Loss for Dense Object Detectioncited by 749
- 2019VideoBERT: A Joint Model for Video and Language Representation Learningcited by 702
- 2016CNN Architectures for Large-Scale Audio Classificationcited by 701
- 2020X3D: Expanding Architectures for Efficient Video Recognitioncited by 635
- 2017Towards Automatic Learning of Procedures from Web Instructional Videoscited by 616
- 2016Hollywood in Homes: Crowdsourcing Data Collection for Activity Understandingcited by 535
- 2017Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classificationcited by 521
- 2016Temporal Convolutional Networks for Action Segmentation and Detectioncited by 504
- 2021VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Textcited by 427
- 2020Multi-modal Transformer for Video Retrievalcited by 395
- 2020Asymmetric Loss For Multi-Label Classificationcited by 379
- 2019MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentationcited by 370
- 2019COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysiscited by 316
- 2020Self-Supervised MultiModal Versatile Networkscited by 276
- 2020TransNet V2: An effective deep network architecture for fast shot transition detectioncited by 166
- 2015Unsupervised Learning from Narrated Instruction Videoscited by 116
- 2015Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videoscited by 93
- 2020Alleviating Over-segmentation Errors by Detecting Action Boundariescited by 86
- 2021Generic Event Boundary Detection: A Benchmark for Event Segmentationcited by 64
- 2020A Local-to-Global Approach to Multi-modal Movie Scene Segmentationcited by 60
- 2020VideoMix: Rethinking Data Augmentation for Video Classificationcited by 55
- 2021Shot Contrastive Self-Supervised Learning for Scene Boundary Detectioncited by 35
- 2018NeXtVLAD: An Efficient Neural Network to Aggregate Frame-level Features for Large-scale Video Classificationcited by 23
- 2015A Deep Siamese Network for Scene Detection in Broadcast Videoscited by 21
- 2017Human Pose Forecasting via Deep Markov Modelscited by 16
- 2019TransNet: A deep network for fast detection of common shot transitionscited by 15
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 1.
2 papers.