In just a few minutes, Georgia Tech researchers summarize their ECCV accepted work in these short videos. Check them out or read their full papers here.
Backpropagated Gradient Representations for Anomaly Detection
By Gukyeong Kwon, Mohit Prabhushankar, Dogancan Temel, and Ghassan AlRegib
ContactPose: A Dataset of Grasps with Object Contact and Hand Pose
By Samarth Brahmbhatt, Chengcheng Tang, Christopher D. Twigg, Charles C. Kemp, and James Hays.
Spatially Aware Multimodal Transformers for TextVQA
By Yash Kant, Dhruv Batra, Peter Anderson, Alex Schwing, Devi Parikh, Jiasen Lu, Harsh Agrawa
Learning to Generate Grounded Visual Captions without Localization Supervision
By Chih-Yao Ma, Yannis Kalantidis, Ghassan AlRegib, Peter Vajda, Marcus Rohrbach, Zsolt Kira
Graph Inference for Knowledge Transfer in Weakly Supervised Object Localization
By Amir Rahimi, Amirreza Shaban, Thalaiyasingam Ajanthan, Richard Hartle, and Byron Boots
Large-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline
By Vishvak Murahari, Dhruv Batra, Devi Parikh, Abhishek Das
Forecasting Human Object Interaction
By Miao Liu, Siyu Tang, Yin Li and James M. Rehg
FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning
By Chia-Wen Kuo, Chih-Yao Ma, Jia-Bin Huang, Zsolt Kira
Improving Vision-and-Language Navigation with Image-Text Pairs from the Web
By Arjun Majumdar, Ayush Shrivastava, Stefan Lee, Peter Anderson, Devi Parikh, Dhruv Batra
TIDE: A General Toolkit for Identifying Object Detection Errors
By Daniel Bolya, Sean Foley, James Hays, Judy Hoffman
Learning to Balance Specificity and Invariance for In and Out of Domain Generalization
By Prithvijit Chattopadyay, Yogesh Balaji, Judy Hoffman