Matches in SemOpenAlex for { <https://semopenalex.org/work/W3215780984> ?p ?o ?g. }
- W3215780984 abstract "First-person action recognition is a challenging task in video understanding. Because of strong ego-motion and a limited field of view, many backgrounds or noisy frames in a first-person video can distract an action recognition model during its learning process. To encode more discriminative features, the model needs to have the ability to focus on the most relevant part of the video for action recognition. Previous works explored to address this problem by applying temporal attention but failed to consider the global context of the full video, which is critical for determining the relatively significant parts. In this work, we propose a simple yet effective Stacked Temporal Attention Module (STAM) to compute temporal attention based on the global knowledge across clips for emphasizing the most discriminative features. We achieve this by stacking multiple self-attention layers. Instead of naive stacking, which is experimentally proven to be ineffective, we carefully design the input to each self-attention layer so that both the local and global context of the video is considered during generating the temporal attention weights. Experiments demonstrate that our proposed STAM can be built on top of most existing backbones and boost the performance in various datasets." @default.
- W3215780984 created "2021-12-06" @default.
- W3215780984 creator A5006040497 @default.
- W3215780984 creator A5018560644 @default.
- W3215780984 creator A5045996641 @default.
- W3215780984 creator A5066894394 @default.
- W3215780984 date "2021-12-02" @default.
- W3215780984 modified "2023-10-01" @default.
- W3215780984 title "Stacked Temporal Attention: Improving First-person Action Recognition by Emphasizing Discriminative Clips" @default.
- W3215780984 cites W1947050545 @default.
- W3215780984 cites W2126579184 @default.
- W3215780984 cites W2156303437 @default.
- W3215780984 cites W2212494831 @default.
- W3215780984 cites W2307770531 @default.
- W3215780984 cites W2432964524 @default.
- W3215780984 cites W2461621749 @default.
- W3215780984 cites W2507009361 @default.
- W3215780984 cites W2556024076 @default.
- W3215780984 cites W2558799462 @default.
- W3215780984 cites W2612445135 @default.
- W3215780984 cites W2770804203 @default.
- W3215780984 cites W2792164665 @default.
- W3215780984 cites W2795307598 @default.
- W3215780984 cites W2885914489 @default.
- W3215780984 cites W2895299763 @default.
- W3215780984 cites W2955874753 @default.
- W3215780984 cites W2962934715 @default.
- W3215780984 cites W2963082988 @default.
- W3215780984 cites W2963246338 @default.
- W3215780984 cites W2963403868 @default.
- W3215780984 cites W2963457877 @default.
- W3215780984 cites W2963524571 @default.
- W3215780984 cites W2963526497 @default.
- W3215780984 cites W2963563276 @default.
- W3215780984 cites W2963853051 @default.
- W3215780984 cites W2964121744 @default.
- W3215780984 cites W2964222622 @default.
- W3215780984 cites W2970971581 @default.
- W3215780984 cites W2971680695 @default.
- W3215780984 cites W2990152177 @default.
- W3215780984 cites W2990503944 @default.
- W3215780984 cites W2995264981 @default.
- W3215780984 cites W2997691861 @default.
- W3215780984 cites W2998384080 @default.
- W3215780984 cites W2999794487 @default.
- W3215780984 cites W3004505825 @default.
- W3215780984 cites W3015458609 @default.
- W3215780984 cites W3037916678 @default.
- W3215780984 cites W3043142510 @default.
- W3215780984 cites W3048602385 @default.
- W3215780984 cites W3105072506 @default.
- W3215780984 cites W3118648637 @default.
- W3215780984 cites W3123364653 @default.
- W3215780984 cites W3169738033 @default.
- W3215780984 cites W3173210343 @default.
- W3215780984 cites W3177419066 @default.
- W3215780984 doi "https://doi.org/10.48550/arxiv.2112.01038" @default.
- W3215780984 hasPublicationYear "2021" @default.
- W3215780984 type Work @default.
- W3215780984 sameAs 3215780984 @default.
- W3215780984 citedByCount "0" @default.
- W3215780984 crossrefType "posted-content" @default.
- W3215780984 hasAuthorship W3215780984A5006040497 @default.
- W3215780984 hasAuthorship W3215780984A5018560644 @default.
- W3215780984 hasAuthorship W3215780984A5045996641 @default.
- W3215780984 hasAuthorship W3215780984A5066894394 @default.
- W3215780984 hasBestOaLocation W32157809841 @default.
- W3215780984 hasConcept C104114177 @default.
- W3215780984 hasConcept C104317684 @default.
- W3215780984 hasConcept C111919701 @default.
- W3215780984 hasConcept C119857082 @default.
- W3215780984 hasConcept C120665830 @default.
- W3215780984 hasConcept C121332964 @default.
- W3215780984 hasConcept C151730666 @default.
- W3215780984 hasConcept C153180895 @default.
- W3215780984 hasConcept C154945302 @default.
- W3215780984 hasConcept C162324750 @default.
- W3215780984 hasConcept C185592680 @default.
- W3215780984 hasConcept C187736073 @default.
- W3215780984 hasConcept C192209626 @default.
- W3215780984 hasConcept C2777212361 @default.
- W3215780984 hasConcept C2779343474 @default.
- W3215780984 hasConcept C2780451532 @default.
- W3215780984 hasConcept C2780791683 @default.
- W3215780984 hasConcept C28490314 @default.
- W3215780984 hasConcept C2987834672 @default.
- W3215780984 hasConcept C41008148 @default.
- W3215780984 hasConcept C55493867 @default.
- W3215780984 hasConcept C62520636 @default.
- W3215780984 hasConcept C66746571 @default.
- W3215780984 hasConcept C86803240 @default.
- W3215780984 hasConcept C97931131 @default.
- W3215780984 hasConcept C98045186 @default.
- W3215780984 hasConceptScore W3215780984C104114177 @default.
- W3215780984 hasConceptScore W3215780984C104317684 @default.
- W3215780984 hasConceptScore W3215780984C111919701 @default.
- W3215780984 hasConceptScore W3215780984C119857082 @default.
- W3215780984 hasConceptScore W3215780984C120665830 @default.
- W3215780984 hasConceptScore W3215780984C121332964 @default.
- W3215780984 hasConceptScore W3215780984C151730666 @default.