Video Classification is the task of producing a label that is relevant to the video given its frames. A good video level classifier is one that not only provides accurate frame labels, but also best describes the entire video given the features and the annotations of the various frames in the video. For example, a video might contain a tree in some frame, but the label that is central to the video might be something else (e.g., “hiking”). The granularity of the labels that are needed to describe the frames and the video depends on the task. Typical tasks include assigning one or more global labels to the video, and assigning one or more labels for each frame inside the video.
FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.
Ranked #45 on
Object Detection
on COCO minival
Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time.
Ranked #8 on
Keypoint Detection
on COCO
(Validation AP metric)
ACTION CLASSIFICATION ACTION RECOGNITION INSTANCE SEGMENTATION KEYPOINT DETECTION OBJECT DETECTION
Using improved training and scaling strategies, we design a family of ResNet architectures, ResNet-RS, which are 1. 7x - 2. 7x faster than EfficientNets on TPUs, while achieving similar accuracies on ImageNet.
Ranked #17 on
Action Classification
on Kinetics-400
ACTION CLASSIFICATION IMAGE CLASSIFICATION VIDEO CLASSIFICATION
This paper presents X3D, a family of efficient video networks that progressively expand a tiny 2D image classification architecture along multiple network axes, in space, time, width and depth.
Ranked #8 on
Action Classification
on Kinetics-400
ACTION CLASSIFICATION FEATURE SELECTION IMAGE CLASSIFICATION VIDEO CLASSIFICATION VIDEO RECOGNITION
We empirically demonstrate a general and robust grid schedule that yields a significant out-of-the-box training speedup without a loss in accuracy for different models (I3D, non-local, SlowFast), datasets (Kinetics, Something-Something, Charades), and training settings (with and without pre-training, 128 GPUs or 1 GPU).
Ranked #1 on
Video Classification
on Kinetics
Therefore, in the present paper, we conduct exploration study in order to improve spatiotemporal 3D CNNs as follows: (i) Recently proposed large-scale video datasets help improve spatiotemporal 3D CNNs in terms of video classification accuracy.
Despite the size of the dataset, some of our models train to convergence in less than a day on a single machine using TensorFlow.
Ranked #2 on
Action Recognition
on ActivityNet
(using extra training data)
Furthermore, based on the temporal segment networks, we won the video classification track at the ActivityNet challenge 2016 among 24 teams, which demonstrates the effectiveness of TSN and the proposed good practices.
Ranked #11 on
Action Classification
on Moments in Time
(Top 5 Accuracy metric)
ACTION CLASSIFICATION ACTION RECOGNITION ACTION RECOGNITION IN VIDEOS ACTION RECOGNITION IN VIDEOS
It is natural to ask: 1) if group convolution can help to alleviate the high computational cost of video classification networks; 2) what factors matter the most in 3D group convolutional networks; and 3) what are good computation/accuracy trade-offs with 3D group convolutional networks.
Ranked #1 on
Action Recognition
on Sports-1M
ACTION CLASSIFICATION ACTION RECOGNITION IMAGE CLASSIFICATION
We demonstrate that using both RNNs (using LSTMs) and Temporal-ConvNets on spatiotemporal feature matrices are able to exploit spatiotemporal dynamics to improve the overall performance.
Ranked #33 on
Action Recognition
on UCF101
ACTION CLASSIFICATION ACTION RECOGNITION VIDEO UNDERSTANDING