Grounded Video Description
arXiv:1812.06587
Abstract
Video description is one of the most challenging problems in vision and language understanding due to the large variability both on the video and language side. Models, hence, typically shortcut the difficulty in recognition and generate plausible sentences that are based on priors but are not necessarily grounded in the video. In this work, we explicitly link the sentence to the evidence in the video by annotating each noun phrase in a sentence with the corresponding bounding box in one of the frames of a video. Our dataset, ActivityNet-Entities, augments the challenging ActivityNet Captions dataset with 158k bounding box annotations, each grounding a noun phrase. This allows training video description models with this data, and importantly, evaluate how grounded or "true" such model are to the video they describe. To generate grounded captions, we propose a novel video description model which is able to exploit these bounding box annotations. We demonstrate the effectiveness of our model on our dataset, but also show how it can be applied to image description on the Flickr30k Entities dataset. We achieve state-of-the-art performance on video description, video paragraph description, and image description and demonstrate our generated sentences are better grounded in the video.
arXiv commentCVPR 2019 oral, camera-ready version including appendix
References in corpus (21)
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Deep Residual Learning for Image Recognition
- Aggregated Residual Transformations for Deep Neural Networks
- Image Captioning with Semantic Attention
- Describing Videos by Exploiting Temporal Structure
- Pythia v0.1: the Winning Entry to the VQA Challenge 2018
- CUHK & ETHZ & SIAT Submission to ActivityNet Challenge 2016
- Women also Snowboard: Overcoming Bias in Captioning Models
- Weakly-Supervised Video Object Grounding from Text by Loss Weighting and Object Interaction
- Attention Correctness in Neural Image Captioning
- CIDEr: Consensus-based Image Description Evaluation
- Boosting Image Captioning with Attributes
- Jointly Localizing and Describing Events for Dense Video Captioning
- Spatio-Temporal Attention Models for Grounded Video Captioning
- Watch What You Just Said: Image Captioning with Text-Conditional Attention
- Generating Descriptions with Grounded and Co-Referenced People
- Video Captioning with Transferred Semantic Attributes
- Attend and Interact: Higher-Order Object Interactions for Video Understanding
- Move Forward and Tell: A Progressive Generator of Video Descriptions
- Spatio-temporal Person Retrieval via Natural Language Queries
- Interpretable Visual Question Answering by Visual Grounding from Attention Supervision Mining