|
|
|
|
| LEADER |
01000caa a22002652 4500 |
| 001 |
NLM373216165 |
| 003 |
DE-627 |
| 005 |
20241108232216.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
240605s2024 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2024.3409078
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1594.xml
|
| 035 |
|
|
|a (DE-627)NLM373216165
|
| 035 |
|
|
|a (NLM)38833398
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Guo, Mingzhe
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Divert More Attention to Vision-Language Object Tracking
|
| 264 |
|
1 |
|c 2024
|
| 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 08.11.2024
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Multimodal vision-language (VL) learning has noticeably pushed the tendency toward generic intelligence owing to emerging large foundation models. However, tracking, as a fundamental vision problem, surprisingly enjoys less bonus from recent flourishing VL learning. We argue that the reasons are two-fold: the lack of large-scale vision-language annotated videos and ineffective vision-language interaction learning of current works. These nuisances motivate us to design more effective vision-language representation for tracking, meanwhile constructing a large database with language annotation for model learning. Particularly, in this paper, we first propose a general attribute annotation strategy to decorate videos in six popular tracking benchmarks, which contributes a large-scale vision-language tracking database with more than 23,000 videos. We then introduce a novel framework to improve tracking by learning a unified-adaptive VL representation, where the cores are the proposed asymmetric architecture search and modality mixer (ModaMixer). To further improve VL representation, we introduce a contrastive loss to align different modalities. To thoroughly evidence the effectiveness of our method, we integrate the proposed framework on three tracking methods with different designs, i.e., the CNN-based SiamCAR (Guo et al. 2020), the Transformer-based OSTrack (Ye et al. 2022), and the hybrid structure TransT (Chen et al. 2021). The experiments demonstrate that our framework can significantly improve all baselines on six benchmarks. Besides empirical results, we theoretically analyze our approach to show its rationality. By revealing the potential of VL representation, we expect the community to divert more attention to VL tracking and hope to open more possibilities for future tracking with diversified multimodal messages
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Zhang, Zhipeng
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Jing, Liping
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Ling, Haibin
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Fan, Heng
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 46(2024), 12 vom: 04. Nov., Seite 8600-8618
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:46
|g year:2024
|g number:12
|g day:04
|g month:11
|g pages:8600-8618
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2024.3409078
|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 46
|j 2024
|e 12
|b 04
|c 11
|h 8600-8618
|