Accepted Papers

Archived Papers:

Our workshop proceedings are published here.

Non archived Papers:

These accepted papers will be presented in the workshop and linked here but will not be part of the workshop proceedings. Papers that are part of CVPR 2023 are marked as such.

Learning text-to-video retrieval from image captioning [paper]

Ventura, Lucas*; Schmid, Cordelia; Varol, Gul

GAPS: Few-Shot Incremental Semantic Segmentation via Guided Copy-Paste Synthesis [paper]

Qiu, Ri-Zhao*; Chen, Peiyi; Sun, Wangzhe; Wang, Yu-Xiong; Hauser, Kris

Rethinking matching-based few-shot action recognition [paper]

Bertrand, Juliette LD*; Kalantidis, Yannis; Tolias, Giorgos

NIFF: Alleviating Forgetting in Generalized Few-Shot Object Detection via Neural Instance Feature Forging [CVPR23]

Guirguis, Karim*; Meier, Johannes; Eskandar, George; Kayser, Matthias; Yang, Bin; Beyerer, Jürgen

FODVid: Flow-guided Object Discovery in Videos [paper]

Singh, Silky*; Deshmukh, Shripad V; Sarkar, Mausoom; Jain, Rishabh; Hemani, Mayur; Krishnamurthy, Balaji

Knowledge Assembly: Semi-Supervised Multi-Task Learning from Multiple Datasets with Disjoint Labels [paper]

Spinola, Federica; Benz , Philipp; Yu, Minhyeong;  Kim, Tae-hoon

LTVRR Challenge Report:

Vision Transformer Based Spatially Conditioned Graphs for Long Tail Visual Relationship Recognition  [paper]

Wang, Chenyu ; Wang, Shuo; Gao, Shenghua