Dear all, I'll be defending my thesis on Tuesday 26th October at 12:00 PM in KEC 1007 and virtually through zoom. Feel free to join either way if you're interested! *Title:* Annotation-Efficient Video Representation Learning *Date & Time:* Tuesday, October 26th at 12:00 pm *Place:* KEC1007 and Zoom Meeting Room. *Abstract:* Labeling videos is costly, time-consuming, and tedious. These costs can escalate in applications such as medical diagnosis, etc. where we need domain expertise for annotation. Few-shot learning in Videos aims to solve this problem by building annotation-efficient learning mechanisms. This thesis presents MetaUVFS as the first Unsupervised Meta-learning algorithm for Video Few-Shot action recognition. MetaUVFS leverages over 550K unlabeled videos to train a two-stream 2D and 3D CNN architecture via contrastive learning to capture the appearance-specific spatial and action-specific Spatio-temporal video features respectively. MetaUVFS comprises a novel Action-Appearance Aligned Meta-adaptation~(A3M) module that learns to focus on the action-oriented video features in relation to the appearance features via explicit few-shot episodic meta-learning over unsupervised hard-mined episodes. Our action-appearance alignment and explicit few-shot learner conditions the unsupervised training to mimic the downstream few-shot task, enabling MetaUVFS to significantly outperform all state-of-the-art unsupervised methods on few-shot benchmarks. Moreover, unlike previous few-shot action recognition methods that are supervised, MetaUVFS needs neither base-class labels nor a supervised pre-trained backbone. Thus, we need to train MetaUVFS just once to perform competitively or sometimes even outperform state-of-the-art supervised methods on popular HMDB51, UCF101, and Kinetics100 few-shot datasets. *Advisor:* Dr. Fuxin Li *Committee:* Dr. Fuxin Li, Dr. Sinisa Todorovic, Dr. Stefan Lee, Dr. Yelda Turkan *Zoom Meeting:* Zoom Meeting details: Paravali, Jay Sanjay is inviting you to a scheduled Zoom meeting. Topic: Jay Patravali MS Robotics Thesis Defense. Time: Oct 26, 2021 12:00 PM Pacific Time (US and Canada) Join Zoom Meeting https://oregonstate.zoom.us/j/91663115146?pwd=bTBXQmFZa1VxM2N6emhxamhEenVrZz... Password: 943745 Phone Dial-In Information +1 971 247 1195 US (Portland) +1 253 215 8782 US (Tacoma) +1 301 715 8592 US (Washington DC) Meeting ID: 916 6311 5146 Join by Polycom/Cisco/Other Room System 91663115146@zoomcrc.com *EECS Department Response on serving Snacks or Coffee:* "The current OSU policy does not allow for serving of such items for events unless they are individually catered. Occupants would need to supply their own coffee and cookies." Thanks, Jay Patravali