| 1. |
- Ardo, Hakan, et al.
(författare)
-
Multi target tracking from drones by learning from generalized graph differences
- 2020
-
Ingår i: Proceedings - 2019 International Conference on Computer Vision : Workshops, ICCVW 2019 - Workshops, ICCVW 2019. - 9781728150239 - 9781728150246 ; , s. 46-54
-
Konferensbidrag (refereegranskat)abstract
- Formulating the multi object tracking problem as a network flow optimization problem is a popular choice. The weights of such network flow problem can be learnt efficiently from training data using a recently introduced concept called Generalized Graph Differences (GGD). This allows a general tracker implementation to be specialized to drone videos by training it on the VisDrone dataset. Two modifications to the original GGD is introduced in this paper and a result with an average precision of 23.09 on the test set of VisDrone 2019 was achieved.
|
|
| 2. |
- Berg, Amanda, 1988-, et al.
(författare)
-
Semi-automatic Annotation of Objects in Visual-Thermal Video
- 2019
-
Ingår i: 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). - : Institute of Electrical and Electronics Engineers (IEEE). - 9781728150239 - 9781728150246
-
Konferensbidrag (refereegranskat)abstract
- Deep learning requires large amounts of annotated data. Manual annotation of objects in video is, regardless of annotation type, a tedious and time-consuming process. In particular, for scarcely used image modalities human annotationis hard to justify. In such cases, semi-automatic annotation provides an acceptable option.In this work, a recursive, semi-automatic annotation method for video is presented. The proposed method utilizesa state-of-the-art video object segmentation method to propose initial annotations for all frames in a video based on only a few manual object segmentations. In the case of a multi-modal dataset, the multi-modality is exploited to refine the proposed annotations even further. The final tentative annotations are presented to the user for manual correction.The method is evaluated on a subset of the RGBT-234 visual-thermal dataset reducing the workload for a human annotator with approximately 78% compared to full manual annotation. Utilizing the proposed pipeline, sequences are annotated for the VOT-RGBT 2019 challenge.
|
|
| 3. |
- Gamba, Matteo, et al.
(författare)
-
On the geometry of rectifier convolutional neural networks
- 2019
-
Ingår i: Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019. - : Institute of Electrical and Electronics Engineers Inc.. - 9781728150239 ; , s. 793-797
-
Konferensbidrag (refereegranskat)abstract
- While recent studies have shed light on the expressivity, complexity and compositionality of convolutional networks, the real inductive bias of the family of functions reachable by gradient descent on natural data is still unknown. By exploiting symmetries in the preactivation space of convolutional layers, we present preliminary empirical evidence of regularities in the preimage of trained rectifier networks, in terms of arrangements of polytopes, and relate it to the nonlinear transformations applied by the network to its input.
|
|
| 4. |
- Konuk, Emir, et al.
(författare)
-
An empirical study of the relation between network architecture and complexity
- 2019
-
Ingår i: Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019. - : Institute of Electrical and Electronics Engineers Inc.. - 9781728150239 ; , s. 4597-4599
-
Konferensbidrag (refereegranskat)abstract
- In this preregistration submission, we propose an empirical study of how networks handle changes in complexity of the data. We investigate the effect of network capacity on generalization performance in the face of increasing data complexity. For this, we measure the generalization error for an image classification task where the number of classes steadily increases. We compare a number of modern architectures at different scales in this setting. The methodology, setup, and hypotheses described in this proposal were evaluated by peer review before experiments were conducted.
|
|
| 5. |
- Kristanl, Matej, et al.
(författare)
-
The Seventh Visual Object Tracking VOT2019 Challenge Results
- 2019
-
Ingår i: 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW). - : IEEE COMPUTER SOC. - 9781728150239 ; , s. 2206-2241
-
Konferensbidrag (refereegranskat)abstract
- The Visual Object Tracking challenge VOT2019 is the seventh annual tracker benchmarking activity organized by the VOT initiative. Results of 81 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 as well as the standard VOT methodology for long-term tracking analysis. The VOT2019 challenge was composed of five challenges focusing on different tracking domains: (i) VOT-ST2019 challenge focused on short-term tracking in RGB, (ii) VOT-RT2019 challenge focused on "real-time" short-term tracking in RGB, (iii) VOT-LT2019 focused on long-term tracking namely coping with target disappearance and reappearance. Two new challenges have been introduced: (iv) VOT-RGBT2019 challenge focused on short-term tracking in RGB and thermal imagery and (v) VOT-RGBD2019 challenge focused on long-term tracking in RGB and depth imagery. The VOT-ST2019, VOT-RT2019 and VOT-LT2019 datasets were refreshed while new datasets were introduced for VOT-RGBT2019 and VOT-RGBD2019. The VOT toolkit has been updated to support both standard short-term, long-term tracking and tracking with multi-channel imagery. 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(1).
|
|
| 6. |
- Linden, E., et al.
(författare)
-
Learning to personalize in appearance-based gaze tracking
- 2019
-
Ingår i: Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019. - : Institute of Electrical and Electronics Engineers Inc.. - 9781728150239 ; , s. 1140-1148
-
Konferensbidrag (refereegranskat)abstract
- Personal variations severely limit the performance of appearance-based gaze tracking. Adapting to these variations using standard neural network model-adaption methods is difficult. The problems range from overfitting, due to small amounts of training data, to underfitting, due to restrictive model architectures. We tackle these problems by introducing SPatial Adaptive GaZe Estimator (SPAZE ). By modeling personal variations as a low-dimensional latent parameter space, SPAZE provides just enough adaptability to capture the range of personal variations without being prone to overfitting. Calibrating SPAZE for a new person reduces to solving a small and simple optimization problem. SPAZE achieves an error of 2.70 degrees on the MPIIGaze dataset, improving on the state-of-the-art by 14 %. We contribute to gaze tracking research by empirically showing that personal variations are well-modeled as a 3-dimensional latent parameter space for each eye. We show that this low-dimensionality is expected by examining model-based approaches to gaze tracking.
|
|
| 7. |
- Zhao, H., et al.
(författare)
-
A simple and robust deep convolutional approach to blind image denoising
- 2019
-
Ingår i: Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019. - : Institute of Electrical and Electronics Engineers Inc.. - 9781728150239 ; , s. 3943-3951
-
Konferensbidrag (refereegranskat)abstract
- Image denoising, particularly Gaussian denoising, has achieved continuous success in the past decades. Although deep convolutional neural networks (CNNs) are also shown leading high-performance in Gaussian denoising just as in many other computer vision tasks, they are not competitive at all on real noisy photographs to representative classical methods such as BM3D and WNNM. In this paper, a simple yet robust method is proposed to improve the effectiveness and practicability of deep denoising models. In view of the difference between real-world noise in camera systems and additive white Gaussian noise (AWGN), the model learning has exploited clean-noisy image pairs newly produced built on a generalized signal dependent noise model. During the model inference, the proposed denoising model is not only blind to the noise type but also to the noise level. Meanwhile, in order to separate the noise from image content as full as possible, a new convolutional architecture is advocated for such a blind denoising task where a kind of lifting residual modules is specifically proposed for discriminative feature extraction. Experimental results on both simulated and real noisy images demonstrate that the proposed blind denoiser achieves fairly competitive or even better performance than state-of-the-art algorithms in terms of both quantitative and qualitative assessment. The codes of the proposed method are available at https://github.com/zhaohengyuan1/SDNet.
|
|
