• Publications
  • Influence
Discriminative figure-centric models for joint action localization and recognition
TLDR
This paper develops an algorithm for action recognition and localization in videos that does not require reliable human detection and tracking as input and uses a figure-centric visual word representation. Expand
Discriminative Latent Models for Recognizing Contextual Group Activities
TLDR
This paper proposes a novel framework for recognizing group activities which jointly captures the group activity, the individual person actions, and the interactions among them and introduces a new feature representation called the action context (AC) descriptor. Expand
TNT: Target-driveN Trajectory Prediction
TLDR
The key insight is that for prediction within a moderate time horizon, the future modes can be effectively captured by a set of target states, which leads to the target-driven trajectory prediction (TNT) framework. Expand
A Hierarchical Representation for Future Action Prediction
TLDR
This work considers inferring the future actions of people from a still image or a short video clip, which aims to capture the subtle details inherent in human movements that may imply a future action. Expand
Retrieving Actions in Group Contexts
TLDR
An action retrieval technique based on rank-SVM, a state-of-the-art approach for solving ranking problems, is developed and the experimental results show the advantage of using contextual information for disambiguating different actions and the benefit of using rank-VMs instead of regular SVMs for video retrieval problems. Expand
Social roles in hierarchical models for human activity recognition
TLDR
A hierarchical model for human activity recognition in entire multi-person scenes, trained in a discriminative max-margin framework, that can improve performance at all considered levels of detail, on two challenging datasets. Expand
Image Retrieval with Structured Object Queries Using Latent Ranking SVM
TLDR
This work develops a learning framework to jointly consider object classes and their relations in image retrieval with structured object queries --- queries that specify the objects that should be present in the scene, and their spatial relations. Expand
Similarity Constrained Latent Support Vector Machine: An Application to Weakly Supervised Action Classification
TLDR
A novel Similarity Constrained Latent Support Vector Machine model is developed to operationalize a model that can classify unseen test videos, as well as localize a region of interest in the video that captures the discriminative essence of the action class. Expand
Action Recognition by Hierarchical Mid-Level Action Elements
TLDR
This work introduces an unsupervised method that is capable of distinguishing action-related segments from background segments and representing actions at multiple spatiotemporal resolutions, and develops structured models that capture a rich set of spatial, temporal and hierarchical relations among the segments. Expand
Beyond Actions: Discriminative Models for Contextual Group Activities
TLDR
The proposed model jointly captures the group activity, the individual person actions, and the interactions among them, and implicitly infer it during learning and inference can significantly improve activity recognition performance. Expand
...
1
2
3
4
...