Search Results for author:
Found 12 papers, 2 papers with code
Disentangled Neural Relational Inference for Interpretable Motion Prediction
The results show superior performance compared to existing methods in modeling spatio-temporal relations, motion prediction, and identifying time-invariant latent features.
Vamos: Versatile Action Models for Video Understanding
What makes good video representations for video understanding, such as anticipating future activities, or answering video-conditioned questions?
Object-centric Video Representation for Long-term Action Anticipation
To recognize and predict human-object interactions, we use a Transformer-based neural architecture which allows the "retrieval" of relevant objects for action anticipation at various time scales.
Ranked #2 on
Long Term Action Anticipation
on Ego4D
Rank2Tell: A Multimodal Driving Dataset for Joint Importance Ranking and Reasoning
The widespread adoption of commercial autonomous vehicles (AVs) and advanced driver assistance systems (ADAS) may largely depend on their acceptance by society, for which their perceived trustworthiness and interpretability to riders are crucial.
AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?
We propose to formulate the LTA task from two perspectives: a bottom-up approach that predicts the next actions autoregressively by modeling temporal dynamics; and a top-down approach that infers the goal of the actor and plans the needed procedure to accomplish the goal.
Weakly-Supervised Action Segmentation and Unseen Error Detection in Anomalous Instructional Videos
We present a novel method for weakly-supervised action segmentation and unseen error detection in anomalous instructional videos.
Latency Matters: Real-Time Action Forecasting Transformer
We present RAFTformer, a real-time action forecasting transformer for latency aware real-world action forecasting applications.
Ordered Atomic Activity for Fine-grained Interactive Traffic Scenario Understanding
We introduce a novel representation called Ordered Atomic Activity for interactive scenario understanding.
AdamsFormer for Spatial Action Localization in the Future
SALF is challenging because it requires understanding the underlying physics of video observations to predict future action locations accurately.
Weakly-Supervised Online Action Segmentation in Multi-View Instructional Videos
Experimental results show efficacy of the proposed methods both qualitatively and quantitatively in two domains of cooking and assembly.
Unsupervised Domain Adaptation for Spatio-Temporal Action Localization
Spatio-temporal action localization is an important problem in computer vision that involves detecting where and when activities occur, and therefore requires modeling of both spatial and temporal features.
Connecting Visual Experiences using Max-flow Network with Application to Visual Localization
This problem is solved by finding the maximum flow in a directed graph flow-network, whose vertices represent the matches between frames in the test and reference sequences.
