Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection
General human action recognition requires understanding of various visual cues. In this paper, we propose a network architecture that computes and integrates the most important visual cues for action recognition: pose, motion, and the raw images. For the integration, we introduce a Markov chain model which adds cues successively. The resulting approach is efficient and applicable to action classification as well as to spatial and temporal action localization. The two contributions clearly improve the performance over respective baselines. The overall approach achieves state-of-the-art action classification performance on HMDB51, J-HMDB and NTU RGB+D datasets. Moreover, it yields state-of-the-art spatio-temporal action localization results on UCF101 and J-HMDB.
Code (1)
Tasks
Action ClassificationAction LocalizationAction RecognitionGeneral ClassificationSkeleton Based Action RecognitionSpatio-Temporal Action LocalizationTemporal Action LocalizationSimilar Papers 제목 키워드 기반
State-switching control of the second-order chained form system
This paper addresses a motion planning problem of the second-order chained form system. The author presents a novel control approach based on switching a state. The second-order chained form system is composed of three s…
FormMotion PlanningMulti-speaker Emotion Conversion via Latent Variable Regularization and a Chained Encoder-Decoder-Predictor Network
We propose a novel method for emotion conversion in speech based on a chained encoder-decoder-predictor neural network architecture. The encoder constructs a latent embedding of the fundamental frequency (F0) contour and…
DecoderSpacecraft Relative Motion Planning Using Chained Chance-Constrained Admissible Sets
With the increasing interest in proximity and docking operations, there is a growing interest in spacecraft relative motion control. This paper extends a previously proposed constrained relative motion approach based on …
Motion PlanningCGNN: Traffic Classification with Graph Neural Network
Traffic classification associates packet streams with known application labels, which is vital for network security and network management. With the rise of NAT, port dynamics, and encrypted traffic, it is increasingly c…
ClassificationGraph Neural NetworkManagementTraffic ClassificationAccurate Esophageal Gross Tumor Volume Segmentation in PET/CT using Two-Stream Chained 3D Deep Network Fusion
Gross tumor volume (GTV) segmentation is a critical step in esophageal cancer radiotherapy treatment planning. Inconsistencies across oncologists and prohibitive labor costs motivate automated approaches for this task. H…
Segmentation