We present an approach to efficiently detect the 2D pose of multiple people in an image. The approach uses a nonparametric representation, which we refer to as Part Affinity Fields (PAFs), to learn to associate body parts with individuals in the image. The architecture encodes global context, allowing a greedy bottom-up parsing step that maintains high accuracy while achieving realtime performance, irrespective of the number of people in the image. The architecture is designed to jointly learn part locations and their association via two branches of the same sequential prediction process. Our method placed first in the inaugural COCO 2016 keypoints challenge, and significantly exceeds the previous state-of-the-art result on the MPII Multi-Person benchmark, both in performance and efficiency.

Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields

In this paper, we are interested in the human pose estimation problem with a focus on learning reliable high-resolution representations. Most existing methods recover high-resolution representations from low-resolution representations produced by a high-to-low resolution network. Instead, our proposed network maintains high-resolution representations through the whole process. We start from a high-resolution subnetwork as the first stage, gradually add high-to-low resolution subnetworks one by one to form more stages, and connect the mutli-resolution subnetworks in parallel. We conduct repeated multi-scale fusions such that each of the high-to-low resolution representations receives information from other parallel representations over and over, leading to rich high-resolution representations. As a result, the predicted keypoint heatmap is potentially more accurate and spatially more precise. We empirically demonstrate the effectiveness of our network through the superior pose estimation results over two benchmark datasets: the COCO keypoint detection dataset and the MPII Human Pose dataset. In addition, we show the superiority of our network in pose tracking on the PoseTrack dataset. The code and models have been publicly available at https://github.com/leoxiaobin/deep-high-resolution-net.pytorch.

/pdf/deep-high-resolution-representation-learning-for-human-pose-145hgz2sfq.pdf

Deep High-Resolution Representation Learning for Human Pose Estimation

We present SlowFast networks for video recognition. Our model involves (i) a Slow pathway, operating at low frame rate, to capture spatial semantics, and (ii) a Fast pathway, operating at high frame rate, to capture motion at fine temporal resolution. The Fast pathway can be made very lightweight by reducing its channel capacity, yet can learn useful temporal information for video recognition. Our models achieve strong performance for both action classification and detection in video, and large improvements are pin-pointed as contributions by our SlowFast concept. We report state-of-the-art accuracy on major video recognition benchmarks, Kinetics, Charades and AVA. Code has been made available at: https://github.com/facebookresearch/SlowFast.

/pdf/slowfast-networks-for-video-recognition-1fmj4pftzn.pdf

SlowFast Networks for Video Recognition

In this paper we discuss several forms of spatiotemporal convolutions for video analysis and study their effects on action recognition. Our motivation stems from the observation that 2D CNNs applied to individual frames of the video have remained solid performers in action recognition. In this work we empirically demonstrate the accuracy advantages of 3D CNNs over 2D CNNs within the framework of residual learning. Furthermore, we show that factorizing the 3D convolutional filters into separate spatial and temporal components yields significantly gains in accuracy. Our empirical study leads to the design of a new spatiotemporal convolutional block "R(2+1)D" which produces CNNs that achieve results comparable or superior to the state-of-the-art on Sports-1M, Kinetics, UCF101, and HMDB51.

/pdf/a-closer-look-at-spatiotemporal-convolutions-for-action-3ke38qctry.pdf

A Closer Look at Spatiotemporal Convolutions for Action Recognition

There has been significant progress on pose estimation and increasing interests on pose tracking in recent years. At the same time, the overall algorithm and system complexity increases as well, making the algorithm analysis and comparison more difficult. This work provides simple and effective baseline methods. They are helpful for inspiring and evaluating new ideas for the field. State-of-the-art results are achieved on challenging benchmarks. The code will be available at https://github.com/leoxiaobin/pose.pytorch.

/pdf/simple-baselines-for-human-pose-estimation-and-tracking-2imd81uzo3.pdf

Simple Baselines for Human Pose Estimation and Tracking

What is a good vector representation of an object? We believe that it should be generative in 3D, in the sense that it can produce new 3D objects; as well as be predictable from 2D, in the sense that it can be perceived from 2D images. We propose a novel architecture, called the TL-embedding network, to learn an embedding space with these properties. The network consists of two components: (a) an autoencoder that ensures the representation is generative; and (b) a convolutional network that ensures the representation is predictable. This enables tackling a number of tasks including voxel prediction from 2D images and 3D model retrieval. Extensive experimental analysis demonstrates the usefulness and versatility of this embedding.

Learning a Predictable and Generative Vector Representation for Objects

We introduce the Action Transformer model for recognizing and localizing human actions in video clips. We repurpose a Transformer-style architecture to aggregate features from the spatiotemporal context around the person whose actions we are trying to classify. We show that by using high-resolution, person-specific, class-agnostic queries, the model spontaneously learns to track individual people and to pick up on semantic context from the actions of others. Additionally its attention mechanism learns to emphasize hands and faces, which are often crucial to discriminate an action – all without explicit supervision other than boxes and class labels. We train and test our Action Transformer network on the Atomic Visual Actions (AVA) dataset, outperforming the state-of-the-art by a significant margin using only raw RGB frames as input.

/pdf/video-action-transformer-network-2f2k9o7wo3.pdf

Video Action Transformer Network

In this work, we introduce a new video representation for action classification that aggregates local convolutional features across the entire spatio-temporal extent of the video. We do so by integrating state-of-the-art two-stream networks [42] with learnable spatio-temporal feature aggregation [6]. The resulting architecture is end-to-end trainable for whole-video classification. We investigate different strategies for pooling across space and time and combining signals from the different streams. We find that: (i) it is important to pool jointly across space and time, but (ii) appearance and motion streams are best aggregated into their own separate representations. Finally, we show that our representation outperforms the two-stream base architecture by a large margin (13% relative) as well as outperforms other baselines with comparable base architectures on HMDB51, UCF101, and Charades video classification benchmarks.

/pdf/actionvlad-learning-spatio-temporal-aggregation-for-action-2pd6jnhsxf.pdf

ActionVLAD: Learning Spatio-Temporal Aggregation for Action Classification

In this work, we introduce a new video representation for action classification that aggregates local convolutional features across the entire spatio-temporal extent of the video. We do so by integrating state-of-the-art two-stream networks with learnable spatio-temporal feature aggregation. The resulting architecture is end-to-end trainable for whole-video classification. We investigate different strategies for pooling across space and time and combining signals from the different streams. We find that: (i) it is important to pool jointly across space and time, but (ii) appearance and motion streams are best aggregated into their own separate representations. Finally, we show that our representation outperforms the two-stream base architecture by a large margin (13% relative) as well as out-performs other baselines with comparable base architectures on HMDB51, UCF101, and Charades video classification benchmarks.

Rohit Girdhar

Papers

Learning a Predictable and Generative Vector Representation for Objects

Learning a Predictable and Generative Vector Representation for Objects

Video Action Transformer Network

ActionVLAD: Learning Spatio-Temporal Aggregation for Action Classification

ActionVLAD: Learning spatio-temporal aggregation for action classification