Self-supervised visual feature learning with deep neural networks: A survey
Large-scale labeled data are generally required to train deep neural networks in order to
obtain better performance in visual feature learning from images or videos for computer …
obtain better performance in visual feature learning from images or videos for computer …
[HTML][HTML] Video-based human activity recognition using deep learning approaches
Due to its capacity to gather vast, high-level data about human activity from wearable or
stationary sensors, human activity recognition substantially impacts people's day-to-day …
stationary sensors, human activity recognition substantially impacts people's day-to-day …
Self-supervised spatiotemporal feature learning via video rotation prediction
The success of deep neural networks generally requires a vast amount of training data to be
labeled, which is expensive and unfeasible in scale, especially for video collections. To …
labeled, which is expensive and unfeasible in scale, especially for video collections. To …
Ship target detection and identification based on SSD_MobilenetV2
Y Zou, L Zhao, S Qin, M Pan, Z Li - 2020 IEEE 5th Information …, 2020 - ieeexplore.ieee.org
There are many deep learning algorithms currently used in ship supervision, but they
generally have the problems of insufficient target detection speed and accurate identification …
generally have the problems of insufficient target detection speed and accurate identification …
[HTML][HTML] Spatial self-attention network with self-attention distillation for fine-grained image recognition
AA Baffour, Z Qin, Y Wang, Z Qin, KKR Choo - Journal of Visual …, 2021 - Elsevier
The underlining task for fine-grained image recognition captures both the inter-class and
intra-class discriminate features. Existing methods generally use auxiliary data to guide the …
intra-class discriminate features. Existing methods generally use auxiliary data to guide the …
Facs3d-net: 3d convolution based spatiotemporal representation for action unit detection
Most approaches to automatic facial action unit (AU) detection consider only spatial
information and ignore AU dynamics. For humans, dynamics improves AU perception. Is …
information and ignore AU dynamics. For humans, dynamics improves AU perception. Is …
3D deformable convolution temporal reasoning network for action recognition
Y Ou, Z Chen - Journal of Visual Communication and Image …, 2023 - Elsevier
Modeling and reasoning of the interactions between multiple entities (actors and objects)
are beneficial for the action recognition task. In this paper, we propose a 3D Deformable …
are beneficial for the action recognition task. In this paper, we propose a 3D Deformable …
Recognizing american sign language manual signs from rgb-d videos
In this paper, we propose a 3D Convolutional Neural Network (3DCNN) based multi-stream
framework to recognize American Sign Language (ASL) manual signs (consisting of …
framework to recognize American Sign Language (ASL) manual signs (consisting of …
Analysis of pruned neural networks (MobileNetV2-YOLO v2) for underwater object detection
Underwater object detection involves the activity of multiple object identification within a
dynamic and noisy environment. Such task is challenging due to the inconsistency of …
dynamic and noisy environment. Such task is challenging due to the inconsistency of …
G‐YOLOX: A Lightweight Network for Detecting Vehicle Types
In recent years, vehicle type detection has had an important role in traffic management. A
lightweight detection network based on multiscale ghost convolution called G‐YOLOX is …
lightweight detection network based on multiscale ghost convolution called G‐YOLOX is …