FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386065649> ?p ?o ?g. }

• W4386065649 abstract "Human pose is typically represented by a coordinate vector of body joints or their heatmap embeddings. While easy for data processing, unrealistic pose estimates are admitted due to the lack of dependency modeling between the body joints. In this paper, we present a structured representation, named Pose as Compositional Tokens (PCT), to explore the joint dependency. It represents a pose by M discrete tokens with each characterizing a sub-structure with several interdependent joints (see Figure 1). The compositional design enables it to achieve a small reconstruction error at a low cost. Then we cast pose estimation as a classification task. In particular, we learn a classifier to predict the categories of the M tokens from an image. A pre-learned decoder network is used to recover the pose from the tokens without further post-processing. We show that it achieves better or comparable pose estimation results as the existing methods in general scenarios, yet continues to work well when occlusion occurs, which is ubiquitous in practice. The code and models are publicly available at https://github.com/Gengzigang/PCT." @default.
• W4386065649 created "2023-08-23" @default.
• W4386065649 creator A5009248953 @default.
• W4386065649 creator A5020141096 @default.
• W4386065649 creator A5073313583 @default.
• W4386065649 creator A5078141810 @default.
• W4386065649 creator A5079916339 @default.
• W4386065649 creator A5084464680 @default.
• W4386065649 date "2023-06-01" @default.
• W4386065649 modified "2023-10-16" @default.
• W4386065649 title "Human Pose as Compositional Tokens" @default.
• W4386065649 cites W1994529670 @default.
• W4386065649 cites W2030536784 @default.
• W4386065649 cites W2036167211 @default.
• W4386065649 cites W2080873731 @default.
• W4386065649 cites W2097151019 @default.
• W4386065649 cites W2101032778 @default.
• W4386065649 cites W2113325037 @default.
• W4386065649 cites W2116626343 @default.
• W4386065649 cites W2117539524 @default.
• W4386065649 cites W2131263044 @default.
• W4386065649 cites W2159564241 @default.
• W4386065649 cites W2330154883 @default.
• W4386065649 cites W2330914857 @default.
• W4386065649 cites W2464305746 @default.
• W4386065649 cites W2518965973 @default.
• W4386065649 cites W2559085405 @default.
• W4386065649 cites W2578797046 @default.
• W4386065649 cites W2612706635 @default.
• W4386065649 cites W2742737904 @default.
• W4386065649 cites W2759748774 @default.
• W4386065649 cites W2798721181 @default.
• W4386065649 cites W2798922769 @default.
• W4386065649 cites W2819476901 @default.
• W4386065649 cites W2916798096 @default.
• W4386065649 cites W2944341987 @default.
• W4386065649 cites W2958537753 @default.
• W4386065649 cites W2962773068 @default.
• W4386065649 cites W2962896489 @default.
• W4386065649 cites W2962954622 @default.
• W4386065649 cites W2963150697 @default.
• W4386065649 cites W2963468256 @default.
• W4386065649 cites W2963474899 @default.
• W4386065649 cites W2963781481 @default.
• W4386065649 cites W2964221239 @default.
• W4386065649 cites W2964297864 @default.
• W4386065649 cites W2964304707 @default.
• W4386065649 cites W2965326519 @default.
• W4386065649 cites W2966735886 @default.
• W4386065649 cites W2968459013 @default.
• W4386065649 cites W2993728126 @default.
• W4386065649 cites W2998273692 @default.
• W4386065649 cites W3014641072 @default.
• W4386065649 cites W3034399482 @default.
• W4386065649 cites W3034464039 @default.
• W4386065649 cites W3034482680 @default.
• W4386065649 cites W3034742259 @default.
• W4386065649 cites W3034750257 @default.
• W4386065649 cites W3035416506 @default.
• W4386065649 cites W3035707711 @default.
• W4386065649 cites W3098612954 @default.
• W4386065649 cites W3109653595 @default.
• W4386065649 cites W3113950706 @default.
• W4386065649 cites W3166539425 @default.
• W4386065649 cites W3169891778 @default.
• W4386065649 cites W3172013121 @default.
• W4386065649 cites W3173811519 @default.
• W4386065649 cites W3173964191 @default.
• W4386065649 cites W3175123126 @default.
• W4386065649 cites W3176892444 @default.
• W4386065649 cites W3177383258 @default.
• W4386065649 cites W3188171292 @default.
• W4386065649 cites W3202716970 @default.
• W4386065649 cites W3203925315 @default.
• W4386065649 cites W4210299223 @default.
• W4386065649 cites W4214508443 @default.
• W4386065649 cites W4214573223 @default.
• W4386065649 cites W4229073080 @default.
• W4386065649 cites W4229618383 @default.
• W4386065649 cites W4229890965 @default.
• W4386065649 cites W4312349930 @default.
• W4386065649 cites W4312804044 @default.
• W4386065649 cites W4312908079 @default.
• W4386065649 cites W4312967365 @default.
• W4386065649 doi "https://doi.org/10.1109/cvpr52729.2023.00071" @default.
• W4386065649 hasPublicationYear "2023" @default.
• W4386065649 type Work @default.
• W4386065649 citedByCount "2" @default.
• W4386065649 countsByYear W43860656492023 @default.
• W4386065649 crossrefType "proceedings-article" @default.
• W4386065649 hasAuthorship W4386065649A5009248953 @default.
• W4386065649 hasAuthorship W4386065649A5020141096 @default.
• W4386065649 hasAuthorship W4386065649A5073313583 @default.
• W4386065649 hasAuthorship W4386065649A5078141810 @default.
• W4386065649 hasAuthorship W4386065649A5079916339 @default.
• W4386065649 hasAuthorship W4386065649A5084464680 @default.
• W4386065649 hasConcept C153180895 @default.
• W4386065649 hasConcept C154945302 @default.
• W4386065649 hasConcept C177264268 @default.
• W4386065649 hasConcept C17744445 @default.

• next