Recognizing human activities from video sequences or still images is a challenging task due
to problems, such as background clutter, partial occlusion, changes in scale, viewpoint …

This paper comprehensively surveys the development of trajectory clustering. Considering
the critical role of trajectory data mining in modern intelligent systems for surveillance …

We present a general and flexible video-level framework for learning action models in
videos. This method, called temporal segment network (TSN), aims to model long-range …

In the face of the video data deluge, today's expensive clip-level classifiers are increasingly
impractical. We propose a framework for efficient action recognition in untrimmed video that …

We propose a new single-shot method for multi-person 3D pose estimation in general
scenes from a monocular RGB camera. Our approach uses novel occlusion-robust pose …

In this paper we present a method to capture video-wide temporal information for action
recognition. We postulate that a function capable of ordering the frames of a video …

We address the problem of action detection in videos. Driven by the latest progress in object
detection from 2D images, we build action models using rich feature hierarchies derived …

We propose a function-based temporal pooling method that captures the latent structure of
the video sequence data-eg, how frame-level features evolve over time in a video. We show …

We introduce the concept of dynamic image, a novel compact representation of videos
useful for video analysis, particularly in combination with convolutional neural networks …

This paper presents a novel approach for analyzing human actions in non-scripted,
unconstrained video settings based on volumetric, xyt, patch classifiers, termed actemes …