Skip to search formSkip to main contentSkip to account menu
The Kinetics Human Action Video Dataset
TLDR
The dataset is described, the statistics are described, how it was collected, and some baseline performance figures for neural network architectures trained and tested for human action classification on this dataset are given.
View PDF on arXiv
Beyond short snippets: Deep networks for video classification
TLDR
This work proposes and evaluates several deep neural network architectures to combine image information across a video over longer time periods than previously attempted, and proposes two methods capable of handling full length videos.
View on IEEE
YouTube-8M: A Large-Scale Video Classification Benchmark
TLDR
YouTube-8M is introduced, the largest multi-label video classification dataset, composed of ~8 million videos (500K hours of video), annotated with a vocabulary of 4800 visual entities, and various (modest) classification models are trained on the dataset.
View PDF on arXiv
AVA: A Video Dataset of Spatio-Temporally Localized Atomic Visual Actions
TLDR
The AVA dataset densely annotates 80 atomic visual actions in 437 15-minute video clips, where actions are localized in space and time, resulting in 1.59M action labels with multiple labels per person occurring frequently.
View on IEEE
Rethinking the Faster R-CNN Architecture for Temporal Action Localization
TLDR
TAL-Net is proposed, an improved approach to temporal action localization in video that is inspired by the Faster RCNN object detection framework and achieves state-of-the-art performance for both action proposal and localization on THUMOS'14 detection benchmark and competitive performance on ActivityNet challenge.
View on IEEE
SfM-Net: Learning of Structure and Motion from Video
TLDR
A geometry-aware neural network for motion estimation in videos that decomposes frame-to-frame pixel motion in terms of scene and object depth, camera motion and 3D object rotations and translations, which often successfully segments the moving objects in the scene.
View PDF on arXiv
Fast, Accurate Detection of 100,000 Object Classes on a Single Machine
Many object detection systems are constrained by the time required to convolve a target image with a bank of filters that code for different aspects of an object's appearance, such as the presence of…
View on IEEE
Efficient region search for object detection
TLDR
This work formulate the objective as an instance of the prize-collecting Steiner tree problem, and shows that for a family of additive classifiers this enables fast search for the optimal object region via a branch-and-cut algorithm.
View on IEEE
What's it going to cost you?: Predicting effort vs. informativeness for multi-label image annotations
TLDR
This work presents an active learning framework that predicts the tradeoff between the effort and information gain associated with a candidate image annotation, thereby ranking unlabeled and partially labeled images according to their expected “net worth” to an object recognition system.
View on IEEE
Hashing Hyperplane Queries to Near Points with Applications to Large-Scale Active Learning
TLDR
This work considers the problem of retrieving the database points nearest to a given hyperplane query without exhaustively scanning the entire database and proposes two hashing-based solutions that use hashing to retrieve near points in sublinear time.
View on IEEE
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License