Search Results for author:
Found 9 papers, 6 papers with code
Learning Higher-order Object Interactions for Keypoint-based Video Understanding
Specifically, KeyNet introduces the use of object based keypoint information to capture context in the scene.
Self-supervised Video Representation Learning with Cascade Positive Retrieval
Implementation-wise, CPR is complementary to pretext tasks and can be easily applied to previous work.
SplitBrain: Hybrid Data and Model Parallel Deep Learning
The recent success of deep learning applications has coincided with those widely available powerful computational resources for training sophisticated machine learning models with huge datasets.
COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality
Group Activity Recognition detects the activity collectively performed by a group of actors, which requires compositional reasoning of actors and objects.
Ranked #2 on
Group Activity Recognition
on Collective Activity
Hopper: Multi-hop Transformer for Spatiotemporal Reasoning
We evaluate over CATER dataset and find that Hopper achieves 73. 2% Top-1 accuracy using just 1 FPS by hopping through just a few critical frames.
Ranked #5 on
Video Object Tracking
on CATER
15 Keypoints Is All You Need
Keypoints are tracked using our Pose Entailment method, in which, first, a pair of pose estimates is sampled from different frames in a video and tokenized.
Ranked #2 on
Pose Tracking
on PoseTrack2017
Contextual Grounding of Natural Language Entities in Images
Next, the model learns the contextual representations of the text tokens and image objects through layers of high-order interaction respectively.
Visual Entailment: A Novel Task for Fine-Grained Image Understanding
We evaluate various existing VQA baselines and build a model called Explainable Visual Entailment (EVE) system to address the VE task.
Ranked #8 on
Visual Entailment
on SNLI-VE test
Visual Entailment Task for Visually-Grounded Language Learning
We introduce a new inference task - Visual Entailment (VE) - which differs from traditional Textual Entailment (TE) tasks whereby a premise is defined by an image, rather than a natural language sentence as in TE tasks.
