| 1. |
- Kristan, Matej, et al.
(författare)
-
The first visual object tracking segmentation VOTS2023 challenge results
- 2023
-
Ingår i: 2023 IEEE/CVF International conference on computer vision workshops (ICCVW). - : Institute of Electrical and Electronics Engineers Inc.. - 9798350307443 - 9798350307450 ; , s. 1788-1810
-
Konferensbidrag (refereegranskat)abstract
- The Visual Object Tracking Segmentation VOTS2023 challenge is the eleventh annual tracker benchmarking activity of the VOT initiative. This challenge is the first to merge short-term and long-term as well as single-target and multiple-target tracking with segmentation masks as the only target location specification. A new dataset was created; the ground truth has been withheld to prevent overfitting. New performance measures and evaluation protocols have been created along with a new toolkit and an evaluation server. Results of the presented 47 trackers indicate that modern tracking frameworks are well-suited to deal with convergence of short-term and long-term tracking and that multiple and single target tracking can be considered a single problem. A leaderboard, with participating trackers details, the source code, the datasets, and the evaluation kit are publicly available at the challenge website1
|
|
| 2. |
- Kristan, Matej, et al.
(författare)
-
The Sixth Visual Object Tracking VOT2018 Challenge Results
- 2019
-
Ingår i: Computer Vision – ECCV 2018 Workshops. - Cham : Springer Publishing Company. - 9783030110086 - 9783030110093 ; , s. 3-53
-
Konferensbidrag (refereegranskat)abstract
- The Visual Object Tracking challenge VOT2018 is the sixth annual tracker benchmarking activity organized by the VOT initiative. Results of over eighty trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years. The evaluation included the standard VOT and other popular methodologies for short-term tracking analysis and a “real-time” experiment simulating a situation where a tracker processes images as if provided by a continuously running sensor. A long-term tracking subchallenge has been introduced to the set of standard VOT sub-challenges. The new subchallenge focuses on long-term tracking properties, namely coping with target disappearance and reappearance. A new dataset has been compiled and a performance evaluation methodology that focuses on long-term tracking capabilities has been adopted. The VOT toolkit has been updated to support both standard short-term and the new long-term tracking subchallenges. Performance of the tested trackers typically by far exceeds standard baselines. The source code for most of the trackers is publicly available from the VOT page. The dataset, the evaluation kit and the results are publicly available at the challenge website (http://votchallenge.net).
|
|
| 3. |
- Xu, Tao, et al.
(författare)
-
Silicon-on-insulator nanopillar-array optical sensor
- 2011
-
Ingår i: Progress in Biomedical Optics and Imaging - Proceedings of SPIE. - : SPIE - International Society for Optical Engineering. - 9780819484451
-
Konferensbidrag (refereegranskat)abstract
- Pillar-array based optical cavities have unique properties, e.g., having a large and connected low dielectric index space (normally air space), having a large percent of electric field energy in air and standing on a substrate. These properties make them well suitable to make ultra compact and highly sensitive label-free optical sensors to detect bio-/chemical reactions. We designed, fabricated, and measured a silicon-on-insulator pillar array microcavity that possesses a quality factor as high as 27,600. We studied its sensitivity for both bulk index change and surface index modification. As a bulk index sensor, for environmental refractive index change of 0.01, a resonance peak wavelength shift of 3.5 nm was measured. As a surface index sensor, the simulations show, for a coating with thickness of 1 nm, the resonance wavelength shifts as large as 2.86 nm. Combining with a sharp 0.06 nm wide resonance peak, our pillar-array sensor is able to resolve ultra small bulk and surface refractive index changes caused by target molecules.
|
|
| 4. |
- Belkin, Liuba, et al.
(författare)
-
When Bad is Good (and Good is Bad):Examining the Ironic Antecedents and Consequences of Bad Behavior
- 2023
-
Ingår i: Academy of Management Annual Meeting Proceedings. - New York : Academy of Management. - 2151-6561 .- 0065-0668.
-
Konferensbidrag (refereegranskat)abstract
- It is a common assumption that organizations should avoid “bad” behaviors, as such behaviors have very few positive outcomes or they are likely motivated by undesirable antecedents. In this symposium, we question this prevailing wisdom, in several ways. We suggest that bad behaviors may both inspire positive outcomes (task performance) and be motivated by seemingly “positive” or innocuous antecedents (gratitude, psychological distance). Additionally, we find that engaging in “bad” behaviors (expressing anger) may have positive relational consequences. Together this symposium explores a series of counterintuitive findings that help explain why bad may be good, and good bad in ways that helps illuminate unexpected behavioral mechanism in workplace relationships.
|
|
| 5. |
- Kristan, Matej, et al.
(författare)
-
The Visual Object Tracking VOT2017 challenge results
- 2017
-
Ingår i: 2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2017). - : IEEE. - 9781538610343 ; , s. 1949-1972
-
Konferensbidrag (refereegranskat)abstract
- The Visual Object Tracking challenge VOT2017 is the fifth annual tracker benchmarking activity organized by the VOT initiative. Results of 51 trackers are presented; many are state-of-the-art published at major computer vision conferences or journals in recent years. The evaluation included the standard VOT and other popular methodologies and a new "real-time" experiment simulating a situation where a tracker processes images as if provided by a continuously running sensor. Performance of the tested trackers typically by far exceeds standard baselines. The source code for most of the trackers is publicly available from the VOT page. The VOT2017 goes beyond its predecessors by (i) improving the VOT public dataset and introducing a separate VOT2017 sequestered dataset, (ii) introducing a realtime tracking experiment and (iii) releasing a redesigned toolkit that supports complex experiments. The dataset, the evaluation kit and the results are publicly available at the challenge website(1).
|
|
| 6. |
- Yam, Kai Chi, et al.
(författare)
-
Feeling Good About Doing Bad: The Unforeseen Positive Emotions and Reactions Underlying Wrongdoing
- 2023
-
Ingår i: Academy of Management Annual Meeting Proceedings. - New York, U.S.A. : Academy of Management. - 2151-6561 .- 0065-0668.
-
Konferensbidrag (refereegranskat)abstract
- Though past research suggests that individuals grapple with negative emotions when dealing with their own and others’ bad (dishonest) behaviors, this symposium explores a different proposition, one where actors feel good for bad deeds in ways that explain why actors and their dishonest collaborators might find extensive support in organizational context. Across a series of studies, the papers in our symposium show that individuals feel pride and gratitude for dishonesty, explaining their motivation to engage in and support dishonesty. Additionally, we find that they are able to reconcile such feelings if they embrace the paradox of feeling bad and good at the same time. Together this research explores the emotional antecedents, consequences, and moderators of positive reactions to dishonesty, providing a more nuanced view as to why dishonesty persists in many organizational contexts.
|
|
| 7. |
|
|
