Weakly Supervised Video Moment Retrieval From Text Queries

Niluthpol Chowdhury Mithun, Sujoy Paul, Amit K. Roy-Chowdhury
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
There have been a few recent methods proposed in text to video moment retrieval using natural language queries, but requiring full supervision during training. However, acquiring a large number of training videos with temporal boundary annotations for each text description is extremely timeconsuming and often not scalable. In order to cope with this issue, in this work, we introduce the problem of learning from weak labels for the task of text to video moment retrieval. The weak nature of the
more » ... pervision is because, during training, we only have access to the video-text pairs rather than the temporal extent of the video to which different text descriptions relate. We propose a joint visualsemantic embedding based framework that learns the notion of relevant segments from video using only video-level sentence descriptions. Specifically, our main idea is to utilize latent alignment between video frames and sentence descriptions using Text-Guided Attention (TGA). TGA is then used during the test phase to retrieve relevant moments. Experiments on two benchmark datasets demonstrate that our method achieves comparable performance to state-of-theart fully supervised approaches.
doi:10.1109/cvpr.2019.01186 dblp:conf/cvpr/MithunPR19 fatcat:fv7y4dhnxrhvjdrf4c2w7mm5nm