toggle visibility Search & Display Options
Select All    Deselect All [1–10] << 11 12 13 14 15 16 17 18 19 20 >> [21–22]
List View
 | 
Citations
 | 
Details
  Records Links
Author Zhijie Fang; Antonio Lopez edit   pdf
url  doi
openurl 
  Title Is the Pedestrian going to Cross? Answering by 2D Pose Estimation Type Conference Article
  Year 2018 Publication IEEE Intelligent Vehicles Symposium Abbreviated Journal  
  Volume Issue Pages 1271 - 1276  
  Keywords (up)  
  Abstract Our recent work suggests that, thanks to nowadays powerful CNNs, image-based 2D pose estimation is a promising cue for determining pedestrian intentions such as crossing the road in the path of the ego-vehicle, stopping before entering the road, and starting to walk or bending towards the road. This statement is based on the results obtained on non-naturalistic sequences (Daimler dataset), i.e. in sequences choreographed specifically for performing the study. Fortunately, a new publicly available dataset (JAAD) has appeared recently to allow developing methods for detecting pedestrian intentions in naturalistic driving conditions; more specifically, for addressing the relevant question is the pedestrian going to cross? Accordingly, in this paper we use JAAD to assess the usefulness of 2D pose estimation for answering such a question. We combine CNN-based pedestrian detection, tracking and pose estimation to predict the crossing action from monocular images. Overall, the proposed pipeline provides new state-ofthe-art results.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference IV  
  Notes ADAS; 600.124; 600.116; 600.118 Approved no  
  Call Number Admin @ si @ FaL2018 Serial 3181  
Permanent link to this record
 
 
Author Jiaolong Xu; Peng Wang; Heng Yang; Antonio Lopez edit   pdf
url  doi
openurl 
  Title Training a Binary Weight Object Detector by Knowledge Transfer for Autonomous Driving Type Conference Article
  Year 2019 Publication IEEE International Conference on Robotics and Automation Abbreviated Journal  
  Volume Issue Pages 2379-2384  
  Keywords (up)  
  Abstract Autonomous driving has harsh requirements of small model size and energy efficiency, in order to enable the embedded system to achieve real-time on-board object detection. Recent deep convolutional neural network based object detectors have achieved state-of-the-art accuracy. However, such models are trained with numerous parameters and their high computational costs and large storage prohibit the deployment to memory and computation resource limited systems. Low-precision neural networks are popular techniques for reducing the computation requirements and memory footprint. Among them, binary weight neural network (BWN) is the extreme case which quantizes the float-point into just bit. BWNs are difficult to train and suffer from accuracy deprecation due to the extreme low-bit representation. To address this problem, we propose a knowledge transfer (KT) method to aid the training of BWN using a full-precision teacher network. We built DarkNet-and MobileNet-based binary weight YOLO-v2 detectors and conduct experiments on KITTI benchmark for car, pedestrian and cyclist detection. The experimental results show that the proposed method maintains high detection accuracy while reducing the model size of DarkNet-YOLO from 257 MB to 8.8 MB and MobileNet-YOLO from 193 MB to 7.9 MB.  
  Address Montreal; Canada; May 2019  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICRA  
  Notes ADAS; 600.124; 600.116; 600.118 Approved no  
  Call Number Admin @ si @ XWY2018 Serial 3182  
Permanent link to this record
 
 
Author Akhil Gurram; Onay Urfalioglu; Ibrahim Halfaoui; Fahd Bouzaraa; Antonio Lopez edit   pdf
doi  openurl
  Title Monocular Depth Estimation by Learning from Heterogeneous Datasets Type Conference Article
  Year 2018 Publication IEEE Intelligent Vehicles Symposium Abbreviated Journal  
  Volume Issue Pages 2176 - 2181  
  Keywords (up)  
  Abstract Depth estimation provides essential information to perform autonomous driving and driver assistance. Especially, Monocular Depth Estimation is interesting from a practical point of view, since using a single camera is cheaper than many other options and avoids the need for continuous calibration strategies as required by stereo-vision approaches. State-of-the-art methods for Monocular Depth Estimation are based on Convolutional Neural Networks (CNNs). A promising line of work consists of introducing additional semantic information about the traffic scene when training CNNs for depth estimation. In practice, this means that the depth data used for CNN training is complemented with images having pixel-wise semantic labels, which usually are difficult to annotate (eg crowded urban images). Moreover, so far it is common practice to assume that the same raw training data is associated with both types of ground truth, ie, depth and semantic labels. The main contribution of this paper is to show that this hard constraint can be circumvented, ie, that we can train CNNs for depth estimation by leveraging the depth and semantic information coming from heterogeneous datasets. In order to illustrate the benefits of our approach, we combine KITTI depth and Cityscapes semantic segmentation datasets, outperforming state-of-the-art results on Monocular Depth Estimation.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference IV  
  Notes ADAS; 600.124; 600.116; 600.118 Approved no  
  Call Number Admin @ si @ GUH2018 Serial 3183  
Permanent link to this record
 
 
Author Gema Rotger; Felipe Lumbreras; Francesc Moreno-Noguer; Antonio Agudo edit   pdf
doi  openurl
  Title 2D-to-3D Facial Expression Transfer Type Conference Article
  Year 2018 Publication 24th International Conference on Pattern Recognition Abbreviated Journal  
  Volume Issue Pages 2008 - 2013  
  Keywords (up)  
  Abstract Automatically changing the expression and physical features of a face from an input image is a topic that has been traditionally tackled in a 2D domain. In this paper, we bring this problem to 3D and propose a framework that given an
input RGB video of a human face under a neutral expression, initially computes his/her 3D shape and then performs a transfer to a new and potentially non-observed expression. For this purpose, we parameterize the rest shape –obtained from standard factorization approaches over the input video– using a triangular
mesh which is further clustered into larger macro-segments. The expression transfer problem is then posed as a direct mapping between this shape and a source shape, such as the blend shapes of an off-the-shelf 3D dataset of human facial expressions. The mapping is resolved to be geometrically consistent between 3D models by requiring points in specific regions to map on semantic
equivalent regions. We validate the approach on several synthetic and real examples of input faces that largely differ from the source shapes, yielding very realistic expression transfers even in cases with topology changes, such as a synthetic video sequence of a single-eyed cyclops.		  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICPR  
  Notes ADAS; 600.086; 600.130; 600.118 Approved no  
  Call Number Admin @ si @ RLM2018 Serial 3232  
Permanent link to this record
 
 
Author Javad Zolfaghari Bengar; Abel Gonzalez-Garcia; Gabriel Villalonga; Bogdan Raducanu; Hamed H. Aghdam; Mikhail Mozerov; Antonio Lopez; Joost Van de Weijer edit   pdf
url  doi
openurl 
  Title Temporal Coherence for Active Learning in Videos Type Conference Article
  Year 2019 Publication IEEE International Conference on Computer Vision Workshops Abbreviated Journal  
  Volume Issue Pages 914-923  
  Keywords (up)  
  Abstract Autonomous driving systems require huge amounts of data to train. Manual annotation of this data is time-consuming and prohibitively expensive since it involves human resources. Therefore, active learning emerged as an alternative to ease this effort and to make data annotation more manageable. In this paper, we introduce a novel active learning approach for object detection in videos by exploiting temporal coherence. Our active learning criterion is based on the estimated number of errors in terms of false positives and false negatives. The detections obtained by the object detector are used to define the nodes of a graph and tracked forward and backward to temporally link the nodes. Minimizing an energy function defined on this graphical model provides estimates of both false positives and false negatives. Additionally, we introduce a synthetic video dataset, called SYNTHIA-AL, specially designed to evaluate active learning for video object detection in road scenes. Finally, we show that our approach outperforms active learning baselines tested on two datasets.  
  Address Seul; Corea; October 2019  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICCVW  
  Notes LAMP; ADAS; 600.124; 602.200; 600.118; 600.120; 600.141 Approved no  
  Call Number Admin @ si @ ZGV2019 Serial 3294  
Permanent link to this record
 
 
Author Hamed H. Aghdam; Abel Gonzalez-Garcia; Joost Van de Weijer; Antonio Lopez edit   pdf
url  doi
openurl 
  Title Active Learning for Deep Detection Neural Networks Type Conference Article
  Year 2019 Publication 18th IEEE International Conference on Computer Vision Abbreviated Journal  
  Volume Issue Pages 3672-3680  
  Keywords (up)  
  Abstract The cost of drawing object bounding boxes (ie labeling) for millions of images is prohibitively high. For instance, labeling pedestrians in a regular urban image could take 35 seconds on average. Active learning aims to reduce the cost of labeling by selecting only those images that are informative to improve the detection network accuracy. In this paper, we propose a method to perform active learning of object detectors based on convolutional neural networks. We propose a new image-level scoring process to rank unlabeled images for their automatic selection, which clearly outperforms classical scores. The proposed method can be applied to videos and sets of still images. In the former case, temporal selection rules can complement our scoring process. As a relevant use case, we extensively study the performance of our method on the task of pedestrian detection. Overall, the experiments show that the proposed method performs better than random selection.  
  Address Seul; Korea; October 2019  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICCV  
  Notes ADAS; LAMP; 600.124; 600.109; 600.141; 600.120; 600.118 Approved no  
  Call Number Admin @ si @ AGW2019 Serial 3321  
Permanent link to this record
 
 
Author Felipe Codevilla; Eder Santana; Antonio Lopez; Adrien Gaidon edit   pdf
url  doi
openurl 
  Title Exploring the Limitations of Behavior Cloning for Autonomous Driving Type Conference Article
  Year 2019 Publication 18th IEEE International Conference on Computer Vision Abbreviated Journal  
  Volume Issue Pages 9328-9337  
  Keywords (up)  
  Abstract Driving requires reacting to a wide variety of complex environment conditions and agent behaviors. Explicitly modeling each possible scenario is unrealistic. In contrast, imitation learning can, in theory, leverage data from large fleets of human-driven cars. Behavior cloning in particular has been successfully used to learn simple visuomotor policies end-to-end, but scaling to the full spectrum of driving behaviors remains an unsolved problem. In this paper, we propose a new benchmark to experimentally investigate the scalability and limitations of behavior cloning. We show that behavior cloning leads to state-of-the-art results, executing complex lateral and longitudinal maneuvers, even in unseen environments, without being explicitly programmed to do so. However, we confirm some limitations of the behavior cloning approach: some well-known limitations (eg, dataset bias and overfitting), new generalization issues (eg, dynamic objects and the lack of a causal modeling), and training instabilities, all requiring further research before behavior cloning can graduate to real-world driving. The code, dataset, benchmark, and agent studied in this paper can be found at github.  
  Address Seul; Korea; October 2019  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICCV  
  Notes ADAS; 600.124; 600.118 Approved no  
  Call Number Admin @ si @ CSL2019 Serial 3322  
Permanent link to this record
 
 
Author Lorenzo Porzi; Markus Hofinger; Idoia Ruiz; Joan Serrat; Samuel Rota Bulo; Peter Kontschieder edit   pdf
url  doi
openurl 
  Title Learning Multi-Object Tracking and Segmentation from Automatic Annotations Type Conference Article
  Year 2020 Publication 33rd IEEE Conference on Computer Vision and Pattern Recognition Abbreviated Journal  
  Volume Issue Pages 6845-6854  
  Keywords (up)  
  Abstract In this work we contribute a novel pipeline to automatically generate training data, and to improve over state-of-the-art multi-object tracking and segmentation (MOTS) methods. Our proposed track mining algorithm turns raw street-level videos into high-fidelity MOTS training data, is scalable and overcomes the need of expensive and time-consuming manual annotation approaches. We leverage state-of-the-art instance segmentation results in combination with optical flow predictions, also trained on automatically harvested training data. Our second major contribution is MOTSNet – a deep learning, tracking-by-detection architecture for MOTS – deploying a novel mask-pooling layer for improved object association over time. Training MOTSNet with our automatically extracted data leads to significantly improved sMOTSA scores on the novel KITTI MOTS dataset (+1.9%/+7.5% on cars/pedestrians), and MOTSNet improves by +4.1% over previously best methods on the MOTSChallenge dataset. Our most impressive finding is that we can improve over previous best-performing works, even in complete absence of manually annotated MOTS training data.  
  Address virtual; June 2020  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference CVPR  
  Notes ADAS; 600.124; 600.118 Approved no  
  Call Number Admin @ si @ PHR2020 Serial 3402  
Permanent link to this record
 
 
Author Diego Porres edit   pdf
url  openurl
  Title Discriminator Synthesis: On reusing the other half of Generative Adversarial Networks Type Conference Article
  Year 2021 Publication Machine Learning for Creativity and Design, Neurips Workshop Abbreviated Journal  
  Volume Issue Pages  
  Keywords (up)  
  Abstract Generative Adversarial Networks have long since revolutionized the world of computer vision and, tied to it, the world of art. Arduous efforts have gone into fully utilizing and stabilizing training so that outputs of the Generator network have the highest possible fidelity, but little has gone into using the Discriminator after training is complete. In this work, we propose to use the latter and show a way to use the features it has learned from the training dataset to both alter an image and generate one from scratch. We name this method Discriminator Dreaming, and the full code can be found at this https URL.  
  Address Virtual; December 2021  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference NEURIPSW  
  Notes ADAS; 601.365 Approved no  
  Call Number Admin @ si @ Por2021 Serial 3597  
Permanent link to this record
 
 
Author Yi Xiao; Felipe Codevilla; Christopher Pal; Antonio Lopez edit   pdf
openurl 
  Title Action-Based Representation Learning for Autonomous Driving Type Conference Article
  Year 2020 Publication Conference on Robot Learning Abbreviated Journal  
  Volume Issue Pages  
  Keywords (up)  
  Abstract Human drivers produce a vast amount of data which could, in principle, be used to improve autonomous driving systems. Unfortunately, seemingly straightforward approaches for creating end-to-end driving models that map sensor data directly into driving actions are problematic in terms of interpretability, and typically have significant difficulty dealing with spurious correlations. Alternatively, we propose to use this kind of action-based driving data for learning representations. Our experiments show that an affordance-based driving model pre-trained with this approach can leverage a relatively small amount of weakly annotated imagery and outperform pure end-to-end driving models, while being more interpretable. Further, we demonstrate how this strategy outperforms previous methods based on learning inverse dynamics models as well as other methods based on heavy human supervision (ImageNet).  
  Address virtual; November 2020  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference CORL  
  Notes ADAS; 600.118 Approved no  
  Call Number Admin @ si @ XCP2020 Serial 3487  
Permanent link to this record
Select All    Deselect All [1–10] << 11 12 13 14 15 16 17 18 19 20 >> [21–22]
List View
 | 
Citations
 | 
Details
toggle visibility
Save Citations:
Export Records: