Matches in SemOpenAlex for { <https://semopenalex.org/work/W4212912983> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4212912983 endingPage "108587" @default.
- W4212912983 startingPage "108587" @default.
- W4212912983 abstract "Video object detection is a challenging task due to the appearance deterioration in video frames. To enhance feature representation of the deteriorated frames, previous methods usually aggregate features from fixed-density and fixed-length adjacent frames. However, due to the redundancy of videos and irregular object movements over time, temporal information may not be efficiently exploited using the traditional inflexible strategy. Alternatively, we present a temporal-adaptive sparse feature aggregation framework, an accurate and efficient method for video object detection. Instead of adopting a fixed-density and fixed-length window fusion strategy, a temporal-adaptive sparse sampling strategy is proposed using a stride predictor to encode informative frames more efficiently. A collaborative feature aggregation framework, which consists of a pixel-adaptive aggregation module and an object-relational aggregation module, is proposed for feature enhancement. The pixel-adaptive aggregation module enhances pixel-level features on the current frame using corresponding pixel-level features from other frames. Similarly, the object-relational aggregation module further enhances feature representation at proposal level. A graph is constructed to model the relations between different proposals so that the relation features and proposal features are adaptively fused for feature enhancement. Experiments demonstrate that our proposed framework significantly surpasses traditional dense aggregation methods, and comprehensive ablation studies verify the effectiveness of each proposed module in our framework." @default.
- W4212912983 created "2022-02-24" @default.
- W4212912983 creator A5003662421 @default.
- W4212912983 creator A5004224507 @default.
- W4212912983 creator A5028693655 @default.
- W4212912983 creator A5057637357 @default.
- W4212912983 date "2022-07-01" @default.
- W4212912983 modified "2023-10-13" @default.
- W4212912983 title "Temporal-adaptive sparse feature aggregation for video object detection" @default.
- W4212912983 cites W2585724928 @default.
- W4212912983 cites W2806722137 @default.
- W4212912983 cites W2962949934 @default.
- W4212912983 cites W2988698702 @default.
- W4212912983 cites W2994356318 @default.
- W4212912983 cites W2996603555 @default.
- W4212912983 cites W3012445982 @default.
- W4212912983 cites W3136957409 @default.
- W4212912983 cites W3187090695 @default.
- W4212912983 doi "https://doi.org/10.1016/j.patcog.2022.108587" @default.
- W4212912983 hasPublicationYear "2022" @default.
- W4212912983 type Work @default.
- W4212912983 citedByCount "6" @default.
- W4212912983 countsByYear W42129129832022 @default.
- W4212912983 countsByYear W42129129832023 @default.
- W4212912983 crossrefType "journal-article" @default.
- W4212912983 hasAuthorship W4212912983A5003662421 @default.
- W4212912983 hasAuthorship W4212912983A5004224507 @default.
- W4212912983 hasAuthorship W4212912983A5028693655 @default.
- W4212912983 hasAuthorship W4212912983A5057637357 @default.
- W4212912983 hasConcept C111919701 @default.
- W4212912983 hasConcept C138885662 @default.
- W4212912983 hasConcept C152124472 @default.
- W4212912983 hasConcept C153180895 @default.
- W4212912983 hasConcept C154945302 @default.
- W4212912983 hasConcept C160633673 @default.
- W4212912983 hasConcept C162319229 @default.
- W4212912983 hasConcept C163797641 @default.
- W4212912983 hasConcept C17744445 @default.
- W4212912983 hasConcept C199360897 @default.
- W4212912983 hasConcept C199539241 @default.
- W4212912983 hasConcept C2776359362 @default.
- W4212912983 hasConcept C2776401178 @default.
- W4212912983 hasConcept C31972630 @default.
- W4212912983 hasConcept C41008148 @default.
- W4212912983 hasConcept C41895202 @default.
- W4212912983 hasConcept C94625758 @default.
- W4212912983 hasConceptScore W4212912983C111919701 @default.
- W4212912983 hasConceptScore W4212912983C138885662 @default.
- W4212912983 hasConceptScore W4212912983C152124472 @default.
- W4212912983 hasConceptScore W4212912983C153180895 @default.
- W4212912983 hasConceptScore W4212912983C154945302 @default.
- W4212912983 hasConceptScore W4212912983C160633673 @default.
- W4212912983 hasConceptScore W4212912983C162319229 @default.
- W4212912983 hasConceptScore W4212912983C163797641 @default.
- W4212912983 hasConceptScore W4212912983C17744445 @default.
- W4212912983 hasConceptScore W4212912983C199360897 @default.
- W4212912983 hasConceptScore W4212912983C199539241 @default.
- W4212912983 hasConceptScore W4212912983C2776359362 @default.
- W4212912983 hasConceptScore W4212912983C2776401178 @default.
- W4212912983 hasConceptScore W4212912983C31972630 @default.
- W4212912983 hasConceptScore W4212912983C41008148 @default.
- W4212912983 hasConceptScore W4212912983C41895202 @default.
- W4212912983 hasConceptScore W4212912983C94625758 @default.
- W4212912983 hasFunder F4320321001 @default.
- W4212912983 hasFunder F4320321133 @default.
- W4212912983 hasFunder F4320322847 @default.
- W4212912983 hasFunder F4320327720 @default.
- W4212912983 hasLocation W42129129831 @default.
- W4212912983 hasOpenAccess W4212912983 @default.
- W4212912983 hasPrimaryLocation W42129129831 @default.
- W4212912983 hasRelatedWork W121273120 @default.
- W4212912983 hasRelatedWork W2002009170 @default.
- W4212912983 hasRelatedWork W2034462085 @default.
- W4212912983 hasRelatedWork W2136485282 @default.
- W4212912983 hasRelatedWork W2141888456 @default.
- W4212912983 hasRelatedWork W2337415362 @default.
- W4212912983 hasRelatedWork W2546871836 @default.
- W4212912983 hasRelatedWork W2740820121 @default.
- W4212912983 hasRelatedWork W317572212 @default.
- W4212912983 hasRelatedWork W4312857205 @default.
- W4212912983 hasVolume "127" @default.
- W4212912983 isParatext "false" @default.
- W4212912983 isRetracted "false" @default.
- W4212912983 workType "article" @default.