| 1. |
- Danelljan, Martin, 1989-, et al.
(författare)
-
Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
- 2016
-
Ingår i: Computer Vision – ECCV 2016. - Cham : Springer. - 9783319464534 - 9783319464541 ; , s. 472-488
-
Konferensbidrag (refereegranskat)abstract
- Discriminative Correlation Filters (DCF) have demonstrated excellent performance for visual object tracking. The key to their success is the ability to efficiently exploit available negative data by including all shifted versions of a training sample. However, the underlying DCF formulation is restricted to single-resolution feature maps, significantly limiting its potential. In this paper, we go beyond the conventional DCF framework and introduce a novel formulation for training continuous convolution filters. We employ an implicit interpolation model to pose the learning problem in the continuous spatial domain. Our proposed formulation enables efficient integration of multi-resolution deep feature maps, leading to superior results on three object tracking benchmarks: OTB-2015 (+5.1% in mean OP), Temple-Color (+4.6% in mean OP), and VOT2015 (20% relative reduction in failure rate). Additionally, our approach is capable of sub-pixel localization, crucial for the task of accurate feature point tracking. We also demonstrate the effectiveness of our learning formulation in extensive feature point tracking experiments.
|
|
| 2. |
- Kristan, Matej, et al.
(författare)
-
The Visual Object Tracking VOT2016 Challenge Results
- 2016
-
Ingår i: COMPUTER VISION - ECCV 2016 WORKSHOPS, PT II. - Cham : SPRINGER INT PUBLISHING AG. - 9783319488813 - 9783319488806 ; , s. 777-823
-
Konferensbidrag (refereegranskat)abstract
- The Visual Object Tracking challenge VOT2016 aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance. Results of 70 trackers are presented, with a large number of trackers being published at major computer vision conferences and journals in the recent years. The number of tested state-of-the-art trackers makes the VOT 2016 the largest and most challenging benchmark on short-term tracking to date. For each participating tracker, a short description is provided in the Appendix. The VOT2016 goes beyond its predecessors by (i) introducing a new semi-automatic ground truth bounding box annotation methodology and (ii) extending the evaluation system with the no-reset experiment.
|
|
| 3. |
- Miftakhova, Regina R., et al.
(författare)
-
Cyclin A1 and P450 Aromatase Promote Metastatic Homing and Growth of Stem-like Prostate Cancer Cells in the Bone Marrow
- 2016
-
Ingår i: Cancer Research. - : American Association for Cancer Research (AACR). - 0008-5472 .- 1538-7445. ; 76:8, s. 2453-2464
-
Tidskriftsartikel (refereegranskat)abstract
- Bone metastasis is a leading cause of morbidity and mortality in prostate cancer. While cancer stem-like cells have been implicated as a cell of origin for prostate cancer metastasis, the pathways that enable metastatic development at distal sites remain largely unknown. In this study, we illuminate pathways relevant to bone metastasis in this disease. We observed that cyclin A1 (CCNA1) protein expression was relatively higher in prostate cancer metastatic lesions in lymph node, lung, and bone/bone marrow. In both primary and metastatic tissues, cyclin A1 expression was also correlated with aromatase(CYP19A1), a key enzyme that directly regulates the local balance of androgens to estrogens. Cyclin A1 overexpression in the stem-like ALDHhigh subpopulation of PC3M cells, one model of prostate cancer, enabled bone marrow integration and metastatic growth. Further, cells obtained from bone marrow metastatic lesions displayed self-renewal capability in colony forming assays. In the bone marrow, cyclin A1 and aromatase enhanced local bonemarrow-releasing factors, including androgen receptor, estrogen and matrix metalloproteinase MMP9 and promoted the metastatic growth of prostate cancer cells. Moreover, ALDHhigh tumor cells expressing elevated levels of aromatase stimulated tumor/host estrogen production and acquired agrowth advantage in the presence of host bone marrow cells.Overall, these findings suggest that local production of steroids and MMPs in the bone marrow may provide a suitable microenvironment for ALDHhigh prostate cancer cells to establish metastatic growths, offering new approaches to therapeutically target bone metastases.
|
|
| 4. |
- Öfjäll, Kristoffer, 1985-, et al.
(författare)
-
Visual Autonomous Road Following by Symbiotic Online Learning
- 2016
-
Ingår i: Intelligent Vehicles Symposium (IV), 2016 IEEE. - 9781509018215 - 9781509018222 ; , s. 136-143
-
Konferensbidrag (refereegranskat)abstract
- Recent years have shown great progress in driving assistance systems, approaching autonomous driving step by step. Many approaches rely on lane markers however, which limits the system to larger paved roads and poses problems during winter. In this work we explore an alternative approach to visual road following based on online learning. The system learns the current visual appearance of the road while the vehicle is operated by a human. When driving onto a new type of road, the human driver will drive for a minute while the system learns. After training, the human driver can let go of the controls. The present work proposes a novel approach to online perception-action learning for the specific problem of road following, which makes interchangeably use of supervised learning (by demonstration), instantaneous reinforcement learning, and unsupervised learning (self-reinforcement learning). The proposed method, symbiotic online learning of associations and regression (SOLAR), extends previous work on qHebb-learning in three ways: priors are introduced to enforce mode selection and to drive learning towards particular goals, the qHebb-learning methods is complemented with a reinforcement variant, and a self-assessment method based on predictive coding is proposed. The SOLAR algorithm is compared to qHebb-learning and deep learning for the task of road following, implemented on a model RC-car. The system demonstrates an ability to learn to follow paved and gravel roads outdoors. Further, the system is evaluated in a controlled indoor environment which provides quantifiable results. The experiments show that the SOLAR algorithm results in autonomous capabilities that go beyond those of existing methods with respect to speed, accuracy, and functionality.
|
|
