[go: up one dir, main page]

Wang et al., 2020 - Google Patents

Deep high-resolution representation learning for visual recognition

Wang et al., 2020

View PDF
Document ID
15505711795824202735
Author
Wang J
Sun K
Cheng T
Jiang B
Deng C
Zhao Y
Liu D
Mu Y
Tan M
Wang X
Liu W
Xiao B
Publication year
Publication venue
IEEE transactions on pattern analysis and machine intelligence

External Links

Snippet

High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the- art frameworks first encode the input image as a low-resolution representation through a …
Continue reading at arxiv.org (PDF) (other versions)

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/36—Image preprocessing, i.e. processing the image information without deciding about the identity of the image
    • G06K9/46—Extraction of features or characteristics of the image
    • G06K9/4604—Detecting partial patterns, e.g. edges or contours, or configurations, e.g. loops, corners, strokes, intersections
    • G06K9/4609—Detecting partial patterns, e.g. edges or contours, or configurations, e.g. loops, corners, strokes, intersections by matching or filtering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/62—Methods or arrangements for recognition using electronic means
    • G06K9/6201—Matching; Proximity measures
    • G06K9/6202—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
    • G06K9/6203—Shifting or otherwise transforming the patterns to accommodate for positional errors
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/62—Methods or arrangements for recognition using electronic means
    • G06K9/6267—Classification techniques
    • G06K9/6268—Classification techniques relating to the classification paradigm, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/62—Methods or arrangements for recognition using electronic means
    • G06K9/6217—Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/62—Methods or arrangements for recognition using electronic means
    • G06K9/68—Methods or arrangements for recognition using electronic means using sequential comparisons of the image signals with a plurality of references in which the sequence of the image signals or the references is relevant, e.g. addressable memory
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/20—Image acquisition
    • G06K9/32—Aligning or centering of the image pick-up or image-field
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/00221—Acquiring or recognising human faces, facial parts, facial sketches, facial expressions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/30—Information retrieval; Database structures therefor; File system structures therefor
    • G06F17/30781—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F17/30784—Information retrieval; Database structures therefor; File system structures therefor of video data using features automatically derived from the video content, e.g. descriptors, fingerprints, signatures, genre
    • G06F17/30799—Information retrieval; Database structures therefor; File system structures therefor of video data using features automatically derived from the video content, e.g. descriptors, fingerprints, signatures, genre using low-level visual features of the video content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K2209/00—Indexing scheme relating to methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformation in the plane of the image, e.g. from bit-mapped to bit-mapped creating a different image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N99/00—Subject matter not provided for in other groups of this subclass

Similar Documents

Publication Publication Date Title
Wang et al. Deep high-resolution representation learning for visual recognition
Liu et al. Part-object relational visual saliency
Munea et al. The progress of human pose estimation: A survey and taxonomy of models applied in 2D human pose estimation
Chen et al. 2D Human pose estimation: A survey
Sun et al. High-resolution representations for labeling pixels and regions
Xu et al. Line segment detection using transformers without edges
Ji et al. Encoder-decoder with cascaded CRFs for semantic segmentation
Chen et al. Learning multi-granular spatio-temporal graph network for skeleton-based action recognition
Chen et al. Banet: Bidirectional aggregation network with occlusion handling for panoptic segmentation
Chen et al. CGMDRNet: Cross-guided modality difference reduction network for RGB-T salient object detection
CN112183545B (en) A method for text recognition in natural scenes with arbitrary shapes
Zhang et al. Deep cascade model-based face recognition: When deep-layered learning meets small data
Zhang et al. A multistage refinement network for salient object detection
Weng et al. Stage-aware feature alignment network for real-time semantic segmentation of street scenes
Yang et al. Hierarchical soft quantization for skeleton-based human action recognition
Fooladgar et al. Multi-modal attention-based fusion model for semantic segmentation of RGB-depth images
Zhou et al. Banet: Boundary-assistant encoder-decoder network for semantic segmentation
Liu et al. Explicit occlusion reasoning for multi-person 3d human pose estimation
Zhang et al. KGSNet: Key-point-guided super-resolution network for pedestrian detection in the wild
He et al. Graph-based progressive fusion network for multi-modality vehicle re-identification
Zhu et al. Mlst-former: Multi-level spatial-temporal transformer for group activity recognition
Lu et al. Paraformer: Parallel attention transformer for efficient feature matching
Cao et al. SipMaskv2: Enhanced fast image and video instance segmentation
Deng et al. Cross-domain detection transformer based on spatial-aware and semantic-aware token alignment
Song et al. Hierarchical edge refinement network for saliency detection