research
∙
07/11/2023
EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone
Video-language pre-training (VLP) has become increasingly important due ...
share
research
∙
06/09/2023
End-to-End Neural Network Compression via ℓ_1/ℓ_2 Regularized Latency Surrogates
Neural network (NN) compression via techniques such as pruning, quantiza...
research
∙
03/31/2023
DIME-FM: DIstilling Multimodal and Efficient Foundation Models
Large Vision-Language Foundation Models (VLFM), such as CLIP, ALIGN and ...
research
∙
11/08/2022
Tell Your Story: Task-Oriented Dialogs for Interactive Content Creation
People capture photos and videos to relive and share memories of persona...
research
∙
10/10/2022