553 citations · 3.5k across the 54 of their papers we have counts for
11 papers · 1 filter
Towards Fairer Datasets: Filtering and Balancing the Distribution of the People Subtree in the ImageNet Hierarchy
Kaiyu Yang, Klint Qinami, Li Fei-Fei +2
Computer vision technology is being used by many but remains representative of only a few. People have reported misbehavior of computer vision models, including offensive predictio…
Compositional Temporal Visual Grounding of Natural Language Event Descriptions
Jonathan C. Stroud, Ryan McCaffrey, Rada Mihalcea +2
Temporal grounding entails establishing a correspondence between natural language event descriptions and their visual depictions. Compositional modeling becomes central: we first g…
Generative Modeling for Small-Data Object Detection
Lanlan Liu, Michael Muelly, Jia Deng +2
This paper explores object detection in the small data regime, where only a limited number of annotated bounding boxes are available due to data rarity and annotation expense. This…
SpatialSense: An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition
Kaiyu Yang, Olga Russakovsky, Jia Deng
Understanding the spatial relations between objects in images is a surprisingly challenging task. A chair may be "behind" a person even if it appears to the left of the person in t…
Feature Partitioning for Efficient Multi-Task Architectures
Alejandro Newell, Lu Jiang, Chong Wang +2
Multi-task learning holds the promise of less data, parameters, and time than training of separate models. We propose a method to automatically search over multi-task architectures…
Learning to Sit: Synthesizing Human-Chair Interactions via Hierarchical Control
Yu-Wei Chao, Jimei Yang, Weifeng Chen +1
Recent progress on physics-based character animation has shown impressive breakthroughs on human motion synthesis, through imitating motion capture data via deep reinforcement lear…