research
∙
03/24/2023
VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretraining
Assessing the aesthetics of an image is challenging, as it is influenced...
share
research
∙
05/12/2022
Weakly-Supervised Action Detection Guided by Audio Narration
Videos are more well-organized curated data sources for visual concept l...
research
∙
05/28/2021
Linguistic Structures as Weak Supervision for Visual Scene Graph Generation
Prior work in scene graph generation requires categorical supervision at...
research
∙
01/04/2021
SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection
Deep learning based object detectors are commonly deployed on mobile dev...
research
∙
07/23/2019
Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection
Learning to localize and name object instances is a fundamental problem ...
research
∙
11/25/2018
Learning to discover and localize visual objects with open vocabulary
To alleviate the cost of obtaining accurate bounding boxes for training ...
research
∙
07/29/2018
Story Understanding in Video Advertisements
In order to resonate with the viewers, many video advertisements explore...
research
∙
11/17/2017
ADVISE: Symbolism and External Knowledge for Decoding Advertisements
In order to convey the most content in their limited space, advertisemen...
research
∙
07/10/2017