Successful active speaker detection requires a three-stage pipeline: (i) audio-visual encoding for all speakers in the clip, (ii) inter-speaker relation modeling between a reference speaker and the background speakers within each frame, and (iii) temporal modeling for the reference speaker.
In this paper, we propose a new deep neural network classifier that simultaneously maximizes the inter-class separation and minimizes the intra-class variation by using the polyhedral conic classification function.
Although motion provides distinctive and complementary information especially for fast moving objects, most of the recent tracking architectures primarily focus on the objects' appearance information.
For this task, we introduce a new video-based benchmark, the Driver Anomaly Detection (DAD) dataset, which contains normal driving videos together with a set of anomalous actions in its training set.
Convolutional Neural Networks with 3D kernels (3D-CNNs) currently achieve state-of-the-art results in video recognition tasks due to their supremacy in extracting spatiotemporal features within video frames.
In this work, we propose an HCI system for dynamic recognition of driver micro hand gestures, which can have a crucial impact in automotive sector especially for safety related issues.
To this end, a lightweight network architecture is introduced and mean teacher, virtual adversarial training and pseudo-labeling algorithms are evaluated on 2D-pose estimation for surgical instruments.
This paper studies unsupervised monocular depth prediction problem.
YOWO is a single-stage architecture with two branches to extract temporal and spatial information concurrently and predict bounding boxes and action probabilities directly from video clips in one evaluation.
Ranked #1 on Action Recognition In Videos on AVA v2.2
Understanding actions and gestures in video streams requires temporal reasoning of the spatial content from different time instants, i. e., spatiotemporal (ST) modeling.
Ranked #112 on Action Recognition on Something-Something V2
The use of hand gestures provides a natural alternative to cumbersome interface devices for Human-Computer Interaction (HCI) systems.
Recently, convolutional neural networks with 3D kernels (3D CNNs) have been very popular in computer vision community as a result of their superior ability of extracting spatio-temporal features within video frames compared to 2D CNNs.
Ranked #2 on Action Recognition In Videos on UCF101
We evaluate our architecture on two publicly available datasets - EgoGesture and NVIDIA Dynamic Hand Gesture Datasets - which require temporal detection and classification of the performed hand gestures.
Ranked #1 on Hand Gesture Recognition on EgoGesture
In this paper, we propose a CNN architecture, Layer Reuse Network (LruNet), where the convolutional layers are used repeatedly without the need of introducing new layers to get a better performance.
Acquiring spatio-temporal states of an action is the most crucial step for action classification.
Ranked #1 on Hand Gesture Recognition on ChaLean test