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.

Abstract: Active learning emerged as an alternative to alleviate the effort to label huge amount of data for data hungry applications (such as image/video indexing and retrieval, autonomous driving, etc.). The goal of active learning is to automatically select a number of unlabeled samples for annotation (according to a budget), based on an acquisition function, which indicates how valuable a sample is for training the model. The learning loss method is a task-agnostic approach which attaches a module to learn to predict the target loss of unlabeled data, and select data with the highest loss for labeling. In this work, we follow this strategy but we define the acquisition function as a learning to rank problem and rethink the structure of the loss prediction module, using a simple but effective listwise approach. Experimental results on four datasets demonstrate that our method outperforms recent state-of-the-art active learning approaches for both image classification and regression tasks.

Abstract: We present a method for exploiting weakly annotated images to improve text extraction pipelines. The approach uses an arbitrary end-to-end text recognition system to obtain text region proposals and their, possibly erroneous, transcriptions. The method includes matching of imprecise transcriptions to weak annotations and an edit distance guided neighbourhood search. It produces nearly error-free, localised instances of scene text, which we treat as “pseudo ground truth” (PGT). The method is applied to two weakly-annotated datasets. Training with the extracted PGT consistently improves the accuracy of a state of the art recognition model, by 3.7% on average, across different benchmark datasets (image domains) and 24.5% on one of the weakly annotated datasets 1 1 Acknowledgements. The authors were supported by Czech Technical University student grant SGS20/171/0HK3/3TJ13, the MEYS VVV project CZ.02.1.01/0.010.0J16 019/0000765 Research Center for Informatics, the Spanish Research project TIN2017-89779-P and the CERCA Programme / Generalitat de Catalunya.

Abstract: This paper addresses the problem of inferring unseen cross-modal image-to-image translations between multiple modalities. We assume that only some of the pairwise translations have been seen (i.e. trained) and infer the remaining unseen translations (where training pairs are not available). We propose mix and match networks, an approach where multiple encoders and decoders are aligned in such a way that the desired translation can be obtained by simply cascading the source encoder and the target decoder, even when they have not interacted during the training stage (i.e. unseen). The main challenge lies in the alignment of the latent representations at the bottlenecks of encoder-decoder pairs. We propose an architecture with several tools to encourage alignment, including autoencoders and robust side information and latent consistency losses. We show the benefits of our approach in terms of effectiveness and scalability compared with other pairwise image-to-image translation approaches. We also propose zero-pair cross-modal image translation, a challenging setting where the objective is inferring semantic segmentation from depth (and vice-versa) without explicit segmentation-depth pairs, and only from two (disjoint) segmentation-RGB and depth-RGB training sets. We observe that a certain part of the shared information between unseen modalities might not be reachable, so we further propose a variant that leverages pseudo-pairs which allows us to exploit this shared information between the unseen modalities

Abstract: BACKGROUND:
Content-based image retrieval (CBIR) is an application of machine learning used to retrieve images by similarity on the basis of features. Our objective was to develop a CBIR system that could identify images containing the same polyp ('polyp fingerprint').
METHODS:
A machine learning technique called Bag of Words was used to describe each endoscopic image containing a polyp in a unique way. The system was tested with 243 white light images belonging to 99 different polyps (for each polyp there were at least two images representing it in two different temporal moments). Images were acquired in routine colonoscopies at Hospital Clínic using high-definition Olympus endoscopes. The method provided for each image the closest match within the dataset.
RESULTS:
The system matched another image of the same polyp in 221/243 cases (91%). No differences were observed in the number of correct matches according to Paris classification (protruded: 90.7% vs. non-protruded: 91.3%) and size (< 10 mm: 91.6% vs. > 10 mm: 90%).
CONCLUSIONS:
A CBIR system can match accurately two images containing the same polyp, which could be a helpful aid for polyp image recognition.
KEYWORDS:
Artificial intelligence; Colorectal polyps; Content-based image retrieval

Abstract: Deep video action recognition models have been highly successful in recent years but require large quantities of manually-annotated data, which are expensive and laborious to obtain. In this work, we investigate the generation of synthetic training data for video action recognition, as synthetic data have been successfully used to supervise models for a variety of other computer vision tasks. We propose an interpretable parametric generative model of human action videos that relies on procedural generation, physics models and other components of modern game engines. With this model we generate a diverse, realistic, and physically plausible dataset of human action videos, called PHAV for “Procedural Human Action Videos”. PHAV contains a total of 39,982 videos, with more than 1000 examples for each of 35 action categories. Our video generation approach is not limited to existing motion capture sequences: 14 of these 35 categories are procedurally-defined synthetic actions. In addition, each video is represented with 6 different data modalities, including RGB, optical flow and pixel-level semantic labels. These modalities are generated almost simultaneously using the Multiple Render Targets feature of modern GPUs. In order to leverage PHAV, we introduce a deep multi-task (i.e. that considers action classes from multiple datasets) representation learning architecture that is able to simultaneously learn from synthetic and real video datasets, even when their action categories differ. Our experiments on the UCF-101 and HMDB-51 benchmarks suggest that combining our large set of synthetic videos with small real-world datasets can boost recognition performance. Our approach also significantly outperforms video representations produced by fine-tuning state-of-the-art unsupervised generative models of videos.

Abstract: This paper summarizes the ChaLearn Looking at People 2020 Challenge on Identity-preserved Human Detection (IPHD). For the purpose, we released a large novel dataset containing more than 112K pairs of spatiotemporally aligned depth and thermal frames (and 175K instances of humans) sampled from 780 sequences. The sequences contain hundreds of non-identifiable people appearing in a mix of in-the-wild and scripted scenarios recorded in public and private places. The competition was divided into three tracks depending on the modalities exploited for the detection: (1) depth, (2) thermal, and (3) depth-thermal fusion. Color was also captured but only used to facilitate the groundtruth annotation. Still the temporal synchronization of three sensory devices is challenging, so bad temporal matches across modalities can occur. Hence, the labels provided should considered “weak”, although test frames were carefully selected to minimize this effect and ensure the fairest comparison of the participants’ results. Despite this added difficulty, the results got by the participants demonstrate current fully-supervised methods can deal with that and achieve outstanding detection performance when measured in terms of AP@0.50.