Three papers on different topics were accepted to ECCV 2020

• The paper titled "Domain Adaptive Semantic Segmentation Using Weak Labels" proposes a unified framework for both unsupervised domain adaptation when using the estimated pseudo-weak labels and the novel scenario of weakly-supervised adaptation when using weak labels acquired from human annotators. This work bridges the gap between unsupervised and full-supervision for semantic segmentation, with none to very little annotation cost.
  
  Title: Domain Adaptive Semantic Segmentation Using Weak Labels
  S. Paul, Y. Tsai, S. Schulter, A. Roy-Chowdhury, M. Chandraker, European Conference on Computer Vision (ECCV), 2020.

• Target Re-identification:
  ​​Title: Exploiting Temporal Coherence for Self-Supervised One-shot Video Re-identification 
  D. Raychaudhuri, A. Roy-Chowdhury, European Conference on Computer Vision (ECCV), 2020.                  

• Adversarial Attacks:
  Title: ​​Connecting the Dots: Detecting Adversarial Perturbations Using Context Inconsistency
  S. Li, S. Zhu, S. Paul, A. Roy-Chowdhury, C. Song, S. Krishnamurthy, A. Swami, K. S Chan, European Conference on Computer Vision (ECCV), 2020.