FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3092878394> ?p ?o ?g. }

• W3092878394 abstract "As we use our hands frequently in daily activities, the analysis of hand-object interactions plays a critical role to many multimedia understanding and interaction applications. Different from conventional 3D hand-only and object-only pose estimation, estimating 3D hand-object pose is more challenging due to the mutual occlusions between hand and object, as well as the physical constraints between them. To overcome these issues, we propose to fully utilize the structural correlations among hand joints and object corners in order to obtain more reliable poses. Our work is inspired by structured output learning models in sequence transduction field like Transformer encoder-decoder framework. Besides modeling inherent dependencies from extracted 2D hand-object pose, our proposed Hand-Object Transformer Network (HOT-Net) also captures the structural correlations among 3D hand joints and object corners. Similar to Transformer's autoregressive decoder, by considering structured output patterns, this helps better constrain the output space and leads to more robust pose estimation. However, different from Transformer's sequential modeling mechanism, HOT-Net adopts a novel non-autoregressive decoding strategy for 3D hand-object pose estimation. Specifically, our model removes the Transformer's dependence on previously generated results and explicitly feeds a reference 3D hand-object pose into the decoding process to provide equivalent target pose patterns for parallely localizing each 3D keypoint. To further improve physical validity of estimated hand pose, besides anatomical constraints, we propose a cooperative pose constraint, aiming to enable the hand pose to cooperate with hand shape, to generate hand mesh. We demonstrate real-time speed and state-of-the-art performance on benchmark hand-object datasets for both 3D hand and object poses." @default.
• W3092878394 created "2020-10-22" @default.
• W3092878394 creator A5005592260 @default.
• W3092878394 creator A5043961617 @default.
• W3092878394 creator A5055403026 @default.
• W3092878394 creator A5081629672 @default.
• W3092878394 creator A5085245110 @default.
• W3092878394 date "2020-10-12" @default.
• W3092878394 modified "2023-10-12" @default.
• W3092878394 title "HOT-Net: Non-Autoregressive Transformer for 3D Hand-Object Pose Estimation" @default.
• W3092878394 cites W1536680647 @default.
• W3092878394 cites W2075156252 @default.
• W3092878394 cites W2150457612 @default.
• W3092878394 cites W2153169563 @default.
• W3092878394 cites W2165272793 @default.
• W3092878394 cites W2194775991 @default.
• W3092878394 cites W2200124539 @default.
• W3092878394 cites W2210697964 @default.
• W3092878394 cites W2227547437 @default.
• W3092878394 cites W2330643967 @default.
• W3092878394 cites W2520346623 @default.
• W3092878394 cites W2522527348 @default.
• W3092878394 cites W2543872873 @default.
• W3092878394 cites W2604236302 @default.
• W3092878394 cites W2605973302 @default.
• W3092878394 cites W2724316534 @default.
• W3092878394 cites W2737305288 @default.
• W3092878394 cites W2768683308 @default.
• W3092878394 cites W2768879211 @default.
• W3092878394 cites W2781143029 @default.
• W3092878394 cites W2799191197 @default.
• W3092878394 cites W2892644985 @default.
• W3092878394 cites W2892814592 @default.
• W3092878394 cites W2896229066 @default.
• W3092878394 cites W2897577167 @default.
• W3092878394 cites W2897765997 @default.
• W3092878394 cites W2962811204 @default.
• W3092878394 cites W2962969034 @default.
• W3092878394 cites W2963207848 @default.
• W3092878394 cites W2963488642 @default.
• W3092878394 cites W2963536265 @default.
• W3092878394 cites W2963756608 @default.
• W3092878394 cites W2963892972 @default.
• W3092878394 cites W2963950354 @default.
• W3092878394 cites W2964093990 @default.
• W3092878394 cites W2964249569 @default.
• W3092878394 cites W2968722025 @default.
• W3092878394 cites W2972662547 @default.
• W3092878394 cites W2982601397 @default.
• W3092878394 cites W2984612350 @default.
• W3092878394 doi "https://doi.org/10.1145/3394171.3413775" @default.
• W3092878394 hasPublicationYear "2020" @default.
• W3092878394 type Work @default.
• W3092878394 sameAs 3092878394 @default.
• W3092878394 citedByCount "34" @default.
• W3092878394 countsByYear W30928783942020 @default.
• W3092878394 countsByYear W30928783942021 @default.
• W3092878394 countsByYear W30928783942022 @default.
• W3092878394 countsByYear W30928783942023 @default.
• W3092878394 crossrefType "proceedings-article" @default.
• W3092878394 hasAuthorship W3092878394A5005592260 @default.
• W3092878394 hasAuthorship W3092878394A5043961617 @default.
• W3092878394 hasAuthorship W3092878394A5055403026 @default.
• W3092878394 hasAuthorship W3092878394A5081629672 @default.
• W3092878394 hasAuthorship W3092878394A5085245110 @default.
• W3092878394 hasConcept C119599485 @default.
• W3092878394 hasConcept C119857082 @default.
• W3092878394 hasConcept C127413603 @default.
• W3092878394 hasConcept C149782125 @default.
• W3092878394 hasConcept C151406439 @default.
• W3092878394 hasConcept C154945302 @default.
• W3092878394 hasConcept C159877910 @default.
• W3092878394 hasConcept C165801399 @default.
• W3092878394 hasConcept C194657046 @default.
• W3092878394 hasConcept C24338571 @default.
• W3092878394 hasConcept C31972630 @default.
• W3092878394 hasConcept C33923547 @default.
• W3092878394 hasConcept C41008148 @default.
• W3092878394 hasConcept C52102323 @default.
• W3092878394 hasConcept C66322947 @default.
• W3092878394 hasConceptScore W3092878394C119599485 @default.
• W3092878394 hasConceptScore W3092878394C119857082 @default.
• W3092878394 hasConceptScore W3092878394C127413603 @default.
• W3092878394 hasConceptScore W3092878394C149782125 @default.
• W3092878394 hasConceptScore W3092878394C151406439 @default.
• W3092878394 hasConceptScore W3092878394C154945302 @default.
• W3092878394 hasConceptScore W3092878394C159877910 @default.
• W3092878394 hasConceptScore W3092878394C165801399 @default.
• W3092878394 hasConceptScore W3092878394C194657046 @default.
• W3092878394 hasConceptScore W3092878394C24338571 @default.
• W3092878394 hasConceptScore W3092878394C31972630 @default.
• W3092878394 hasConceptScore W3092878394C33923547 @default.
• W3092878394 hasConceptScore W3092878394C41008148 @default.
• W3092878394 hasConceptScore W3092878394C52102323 @default.
• W3092878394 hasConceptScore W3092878394C66322947 @default.
• W3092878394 hasLocation W30928783941 @default.
• W3092878394 hasOpenAccess W3092878394 @default.
• W3092878394 hasPrimaryLocation W30928783941 @default.
• W3092878394 hasRelatedWork W1968716783 @default.
• W3092878394 hasRelatedWork W2567319754 @default.

• next