Fusion that matters: convolutional fusion networks for visual recognition
Sign Up to like & getrecommendations! Published in 2018 at "Multimedia Tools and Applications"
DOI: 10.1007/s11042-018-5691-4
Abstract: In recent years, deep learning has been successfully applied to diverse multimedia research areas, with the aim of learning powerful and informative representations for a variety of visual recognition tasks. In this work, we propose… read more here.
Keywords: fusion networks; convolutional fusion; fusion matters; fusion ... See more keywords
Active Perception in Non-Visual Recognition Environments by Stretchable Tentacle Sensor Arrays.
Sign Up to like & getrecommendations! Published in 2022 at "ACS applied materials & interfaces"
DOI: 10.1021/acsami.2c04717
Abstract: Smoke fog or other light-interference environments have intrinsic obstruction for visual recognition techniques to explore objects and surroundings. Alternatively, tactile perceptions, rather than visual observations, are commonly used by burrowing or deep-sea animals to communicate… read more here.
Keywords: visual recognition; tentacle sensor; tentacle; non visual ... See more keywords
Long-Tailed Visual Recognition via Improved Cross-Window Self-Attention and TrivialAugment
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Access"
DOI: 10.1109/access.2023.3277204
Abstract: In the real world, large-scale image data sets usually present long-tailed distribution. When traditional visual recognition methods are applied to long-tail image data sets, problems such as model failure and sudden decline in recognition accuracy… read more here.
Keywords: recognition; visual recognition; long tailed; self attention ... See more keywords
Geometry-Aware Similarity Learning on SPD Manifolds for Visual Recognition
Sign Up to like & getrecommendations! Published in 2018 at "IEEE Transactions on Circuits and Systems for Video Technology"
DOI: 10.1109/tcsvt.2017.2729660
Abstract: Symmetric positive definite (SPD) matrices have been employed for data representation in many visual recognition tasks. The success is mainly attributed to learning discriminative SPD matrices encoding the Riemannian geometry of the underlying SPD manifolds.… read more here.
Keywords: similarity learning; spd manifolds; geometry; geometry aware ... See more keywords
Attentive Feature Augmentation for Long-Tailed Visual Recognition
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Circuits and Systems for Video Technology"
DOI: 10.1109/tcsvt.2022.3161427
Abstract: Deep neural networks have achieved great success on many visual recognition tasks. However, training data with a long-tailed distribution dramatically degenerates the performance of recognition models. In order to relieve this imbalance problem, an effective… read more here.
Keywords: recognition; visual recognition; tailed visual; long tailed ... See more keywords
Deep Attention-Based Spatially Recursive Networks for Fine-Grained Visual Recognition
Sign Up to like & getrecommendations! Published in 2019 at "IEEE Transactions on Cybernetics"
DOI: 10.1109/tcyb.2018.2813971
Abstract: Fine-grained visual recognition is an important problem in pattern recognition applications. However, it is a challenging task due to the subtle interclass difference and large intraclass variation. Recent visual attention models are able to automatically… read more here.
Keywords: attention; grained visual; visual recognition; fine grained ... See more keywords
Enhance Visual Recognition Under Adverse Conditions via Deep Networks
Sign Up to like & getrecommendations! Published in 2019 at "IEEE Transactions on Image Processing"
DOI: 10.1109/tip.2019.2908802
Abstract: Visual recognition under adverse conditions is a very important and challenging problem of high practical value, due to the ubiquitous existence of quality distortions during image acquisition, transmission, or storage. While deep neural networks have… read more here.
Keywords: recognition adverse; adverse conditions; visual recognition; image ... See more keywords
Sample Balancing for Deep Learning-Based Visual Recognition
Sign Up to like & getrecommendations! Published in 2020 at "IEEE Transactions on Neural Networks and Learning Systems"
DOI: 10.1109/tnnls.2019.2947789
Abstract: Sample balancing includes sample selection and sample reweighting. Sample selection aims to remove some bad samples that may lead to bad local optima. Sample reweighting aims to assign optimal weights to samples to improve performance.… read more here.
Keywords: sample balancing; visual recognition; sample selection; deep learning ... See more keywords
Collaborative Active Visual Recognition from Crowds: A Distributed Ensemble Approach
Sign Up to like & getrecommendations! Published in 2018 at "IEEE Transactions on Pattern Analysis and Machine Intelligence"
DOI: 10.1109/tpami.2017.2682082
Abstract: Active learning is an effective way of engaging users to interactively train models for visual recognition more efficiently. The vast majority of previous works focused on active learning with a single human oracle. The problem… read more here.
Keywords: active learning; visual recognition; recognition crowds; active visual ... See more keywords
Learning Versatile Convolution Filters for Efficient Visual Recognition
Sign Up to like & getrecommendations! Published in 2021 at "IEEE transactions on pattern analysis and machine intelligence"
DOI: 10.1109/tpami.2021.3114368
Abstract: This paper introduces versatile filters to construct efficient convolutional neural networks that are widely used in various visual recognition tasks. Considering the demands of efficient deep learning techniques running on cost-effective hardware, a number of… read more here.
Keywords: versatile filters; convolution; learning versatile; neural networks ... See more keywords
Glance and Focus Networks for Dynamic Visual Recognition
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Pattern Analysis and Machine Intelligence"
DOI: 10.1109/tpami.2022.3196959
Abstract: Spatial redundancy widely exists in visual recognition tasks, i.e., discriminative features in an image or video frame usually correspond to only a subset of pixels, while the remaining regions are irrelevant to the task at… read more here.
Keywords: recognition; visual recognition; image; glance focus ... See more keywords