Li Fei-Fei

TL;DR: This work proposes to train an agent to fuse a large set of visual representations that correspond to diverse visual perception abilities, and develops an action-level representation fusion scheme, which predicts an action candidate from each representation and adaptively consolidate these action candidates into the final action.

TL;DR: In this article, the authors propose to learn temporal embeddings of video frames for complex video analysis by incorporating temporal context based on past and future frames in videos, and compare this to other contextual representations.

TL;DR: This work proposes an unsupervised method for reference resolution in instructional videos, where the goal is to temporally link an entity to the action that produced it, and learns a joint visual-linguistic model, where linguistic cues can help resolve visual ambiguities and vice versa.

TL;DR: This work introduces a scalable knowledge base construction system that is capable of building a KB with half billion variables and millions of parameters in a few hours, and achieves competitive results compared to purpose-built models on standard recognition and retrieval tasks, while exhibiting greater flexibility in answering richer visual queries.

TL;DR: Zhao et al. as mentioned in this paper proposed a model based on adversarial training with two competing objectives to learn features that have maximum discriminative power with respect to the task and minimal statistical mean dependence with the protected (bias) variable(s).