File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1007/978-3-319-46478-7_9
- Scopus: eid_2-s2.0-84990038547
- WOS: WOS:000389500100009
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: A siamese long short-term memory architecture for human re-identification
Title | A siamese long short-term memory architecture for human re-identification |
---|---|
Authors | |
Keywords | Contextual dependency Human re-identification Long-Short Term Memory Siamese architecture |
Issue Date | 2016 |
Publisher | Springer |
Citation | 14th European Conference on Computer Vision (ECCV 2016), Amsterdam, The Netherlands, 11-14 October 2016. In Leibe, B, Matas, J, Sebe, N, et al. (Eds.), Computer Vision - ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VII, p. 135-153. Cham, Switzerland: Springer, 2016 How to Cite? |
Abstract | Matching pedestrians across multiple camera views known as human re-identification (re-identification) is a challenging problem in visual surveillance. In the existing works concentrating on feature extraction, representations are formed locally and independent of other regions. We present a novel siamese Long Short-Term Memory (LSTM) architecture that can process image regions sequentially and enhance the discriminative capability of local feature representation by leveraging contextual information. The feedback connections and internal gating mechanism of the LSTM cells enable our model to memorize the spatial dependencies and selectively propagate relevant contextual information through the network. We demonstrate improved performance compared to the baseline algorithm with no LSTM units and promising results compared to state-of-the-art methods on Market-1501, CUHK03 and VIPeR datasets. Visualization of the internal mechanism of LSTM cells shows meaningful patterns can be learned by our method. |
Persistent Identifier | http://hdl.handle.net/10722/321704 |
ISBN | |
ISSN | 2023 SCImago Journal Rankings: 0.606 |
ISI Accession Number ID | |
Series/Report no. | Lecture Notes in Computer Science ; 9911 LNCS Sublibrary. SL 6, Image Processing, Computer Vision, Pattern Recognition, and Graphics |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Varior, Rahul Rama | - |
dc.contributor.author | Shuai, Bing | - |
dc.contributor.author | Lu, Jiwen | - |
dc.contributor.author | Xu, Dong | - |
dc.contributor.author | Wang, Gang | - |
dc.date.accessioned | 2022-11-03T02:20:54Z | - |
dc.date.available | 2022-11-03T02:20:54Z | - |
dc.date.issued | 2016 | - |
dc.identifier.citation | 14th European Conference on Computer Vision (ECCV 2016), Amsterdam, The Netherlands, 11-14 October 2016. In Leibe, B, Matas, J, Sebe, N, et al. (Eds.), Computer Vision - ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VII, p. 135-153. Cham, Switzerland: Springer, 2016 | - |
dc.identifier.isbn | 9783319464770 | - |
dc.identifier.issn | 0302-9743 | - |
dc.identifier.uri | http://hdl.handle.net/10722/321704 | - |
dc.description.abstract | Matching pedestrians across multiple camera views known as human re-identification (re-identification) is a challenging problem in visual surveillance. In the existing works concentrating on feature extraction, representations are formed locally and independent of other regions. We present a novel siamese Long Short-Term Memory (LSTM) architecture that can process image regions sequentially and enhance the discriminative capability of local feature representation by leveraging contextual information. The feedback connections and internal gating mechanism of the LSTM cells enable our model to memorize the spatial dependencies and selectively propagate relevant contextual information through the network. We demonstrate improved performance compared to the baseline algorithm with no LSTM units and promising results compared to state-of-the-art methods on Market-1501, CUHK03 and VIPeR datasets. Visualization of the internal mechanism of LSTM cells shows meaningful patterns can be learned by our method. | - |
dc.language | eng | - |
dc.publisher | Springer | - |
dc.relation.ispartof | Computer Vision - ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VII | - |
dc.relation.ispartofseries | Lecture Notes in Computer Science ; 9911 | - |
dc.relation.ispartofseries | LNCS Sublibrary. SL 6, Image Processing, Computer Vision, Pattern Recognition, and Graphics | - |
dc.subject | Contextual dependency | - |
dc.subject | Human re-identification | - |
dc.subject | Long-Short Term Memory | - |
dc.subject | Siamese architecture | - |
dc.title | A siamese long short-term memory architecture for human re-identification | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1007/978-3-319-46478-7_9 | - |
dc.identifier.scopus | eid_2-s2.0-84990038547 | - |
dc.identifier.spage | 135 | - |
dc.identifier.epage | 153 | - |
dc.identifier.eissn | 1611-3349 | - |
dc.identifier.isi | WOS:000389500100009 | - |
dc.publisher.place | Cham, Switzerland | - |