This paper focuses on temporal localization of actions in untrimmed videos. Existing methods typically train classifiers for a pre-defined list of actions and apply them in a sliding window fashion. However, activities in the wild consist of a wide combination of actors, actions and objects; it is difficult to design a proper activity list that meets users' needs. We propose to localize activities by natural language queries. Temporal Activity Localization via Language (TALL) is challenging as it requires: (1) suitable design of text and video representations to allow cross-modal matching of actions and language queries; (2) ability to locate actions accurately given features from sliding windows of limited granularity. We propose a novel Cross-modal Temporal Regression Localizer (CTRL) to jointly model text query and video clips, output alignment scores and action boundary regression results for candidate clips. For evaluation, we adopt TaCoS dataset, and build a new dataset for this task on top of Charades by adding sentence temporal annotations, called Charades-STA. We also build complex sentence queries in Charades-STA for test. Experimental results show that CTRL outperforms previous methods significantly on both datasets.

Detection and tracking of humans in video streams is important for many applications. We present an approach to automatically detect and track multiple, possibly partially occluded humans in a walking or standing pose from a single camera, which may be stationary or moving. A human body is represented as an assembly of body parts. Part detectors are learned by boosting a number of weak classifiers which are based on edgelet features. Responses of part detectors are combined to form a joint likelihood model that includes an analysis of possible occlusions. The combined detection responses and the part detection responses provide the observations used for tracking. Trajectory initialization and termination are both automatic and rely on the confidences computed from the detection responses. An object is tracked by data association and meanshift methods. Our system can track humans with both inter-object and scene occlusions with static or non-static backgrounds. Evaluation results on a number of images and videos and comparisons with some previous methods are given.

Temporal Action Proposal (TAP) generation is an important problem, as fast and accurate extraction of semantically important (e.g. human actions) segments from untrimmed videos is an important step for large-scale video analysis. We propose a novel Temporal Unit Regression Network (TURN) model. There are two salient aspects of TURN: (1) TURN jointly predicts action proposals and refines the temporal boundaries by temporal coordinate regression; (2) Fast computation is enabled by unit feature reuse: a long untrimmed video is decomposed into video units, which are reused as basic building blocks of temporal proposals. TURN outperforms the previous state-of-theart methods under average recall (AR) by a large margin on THUMOS-14 and ActivityNet datasets, and runs at over 880 frames per second (FPS) on a TITAN X GPU. We further apply TURN as a proposal generation stage for existing temporal action localization pipelines, it outperforms stateof-the-art performance on THUMOS-14 and ActivityNet.

No abstract