Towards Real-World Visual Tracking With Temporal Contexts

Towards Real-World Visual Tracking With Temporal Contexts

Visual tracking has made significant improvements in the past few decades. Most existing state-of-the-art trackers 1) merely aim for performance in ideal conditions while overlooking the real-world conditions; 2) adopt the tracking-by-detection paradigm, neglecting rich temporal contexts; 3) only in...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 12 vom: 01. Dez., Seite 15834-15849
1. Verfasser: Cao, Ziang (VerfasserIn)
Weitere Verfasser: Huang, Ziyuan, Pan, Liang, Zhang, Shiwei, Liu, Ziwei, Fu, Changhong
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2023
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM361056966
003 DE-627
005 20231226084334.0
007 cr uuu---uuuuu
008 231226s2023 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2023.3307174  |2 doi 
028 5 2 |a pubmed24n1203.xml 
035 |a (DE-627)NLM361056966 
035 |a (NLM)37607139 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Cao, Ziang  |e verfasserin  |4 aut 
245 1 0 |a Towards Real-World Visual Tracking With Temporal Contexts 
264 1 |c 2023 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 07.11.2023 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Visual tracking has made significant improvements in the past few decades. Most existing state-of-the-art trackers 1) merely aim for performance in ideal conditions while overlooking the real-world conditions; 2) adopt the tracking-by-detection paradigm, neglecting rich temporal contexts; 3) only integrate the temporal information into the template, where temporal contexts among consecutive frames are far from being fully utilized. To handle those problems, we propose a two-level framework (TCTrack) that can exploit temporal contexts efficiently. Based on it, we propose a stronger version for real-world visual tracking, i.e., TCTrack++. It boils down to two levels: features and similarity maps. Specifically, for feature extraction, we propose an attention-based temporally adaptive convolution to enhance the spatial features using temporal information, which is achieved by dynamically calibrating the convolution weights. For similarity map refinement, we introduce an adaptive temporal transformer to encode the temporal knowledge efficiently and decode it for the accurate refinement of the similarity map. To further improve the performance, we additionally introduce a curriculum learning strategy. Also, we adopt online evaluation to measure performance in real-world conditions. Exhaustive experiments on 8 well-known benchmarks demonstrate the superiority of TCTrack++. Real-world tests directly verify that TCTrack++ can be readily used in real-world applications 
650 4 |a Journal Article 
700 1 |a Huang, Ziyuan  |e verfasserin  |4 aut 
700 1 |a Pan, Liang  |e verfasserin  |4 aut 
700 1 |a Zhang, Shiwei  |e verfasserin  |4 aut 
700 1 |a Liu, Ziwei  |e verfasserin  |4 aut 
700 1 |a Fu, Changhong  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 45(2023), 12 vom: 01. Dez., Seite 15834-15849  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:45  |g year:2023  |g number:12  |g day:01  |g month:12  |g pages:15834-15849 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2023.3307174  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 45  |j 2023  |e 12  |b 01  |c 12  |h 15834-15849