由于卷积神经网络（CNN）在过去的十年中检测成功，多对象跟踪（MOT）通过检测方法的使用来控制。随着数据集和基础标记网站的发布，研究方向已转向在跟踪时在包括重新识别对象的通用场景（包括重新识别（REID））上的最佳准确性。在这项研究中，我们通过提供专用的行人数据集并专注于对性能良好的多对象跟踪器的深入分析来缩小监视的范围）现实世界应用的技术。为此，我们介绍SOMPT22数据集；一套新的，用于多人跟踪的新套装，带有带注释的简短视频，该视频从位于杆子上的静态摄像头捕获，高度为6-8米，用于城市监视。与公共MOT数据集相比，这提供了室外监视的MOT的更为集中和具体的基准。我们分析了该新数据集上检测和REID网络的使用方式，分析了将MOT跟踪器分类为单发和两阶段。我们新数据集的实验结果表明，SOTA远非高效率，而单一跟踪器是统一快速执行和准确性的良好候选者，并具有竞争性的性能。该数据集将在以下网址提供：sompt22.github.io

文本分类问题是自然语言处理领域的一个非常广泛的研究领域。简而言之，文本分类问题是确定给定文本所属的先前确定的哪个类别。在过去的研究中，在这一领域进行了成功的研究。在该研究中，使用用于变压器（BERT）的双向编码器表示，其是用于解决自然语言处理领域中的分类问题的常用方法。通过通过在Chatbot架构中使用的单个模型来解决分类问题，旨在缓解服务器上的负载，该负载将由一个以上的模型创建，用于解决多个分类问题。此时，利用在估计在多于一个主题中为分类而创建的单个BERT模型期间应用的掩蔽方法，基于问题的基础提供了模型的估计。覆盖不同字段的三个单独的数据集被各种方法除以各种方法，以使问题复杂化，并且在这种方式中也包括在字段中彼此非常接近的分类问题。以这种方式使用的数据集包括五个课程的五个分类问题。在性能和服务器上占用的空间方面相互比较包含所有分类问题和专门用于问题的其他BERT模型的BERT模型。

Object detectors are conventionally trained by a weighted sum of classification and localization losses. Recent studies (e.g., predicting IoU with an auxiliary head, Generalized Focal Loss, Rank & Sort Loss) have shown that forcing these two loss terms to interact with each other in non-conventional ways creates a useful inductive bias and improves performance. Inspired by these works, we focus on the correlation between classification and localization and make two main contributions: (i) We provide an analysis about the effects of correlation between classification and localization tasks in object detectors. We identify why correlation affects the performance of various NMS-based and NMS-free detectors, and we devise measures to evaluate the effect of correlation and use them to analyze common detectors. (ii) Motivated by our observations, e.g., that NMS-free detectors can also benefit from correlation, we propose Correlation Loss, a novel plug-in loss function that improves the performance of various object detectors by directly optimizing correlation coefficients: E.g., Correlation Loss on Sparse R-CNN, an NMS-free method, yields 1.6 AP gain on COCO and 1.8 AP gain on Cityscapes dataset. Our best model on Sparse R-CNN reaches 51.0 AP without test-time augmentation on COCO test-dev, reaching state-of-the-art. Code is available at https://github.com/fehmikahraman/CorrLoss

This paper expounds the design and control of a new Variable Stiffness Series Elastic Actuator (VSSEA). It is established by employing a modular mechanical design approach that allows us to effectively optimise the stiffness modulation characteristics and power density of the actuator. The proposed VSSEA possesses the following features: i) no limitation in the work-range of output link, ii) a wide range of stiffness modulation (~20Nm/rad to ~1KNm/rad), iii) low-energy-cost stiffness modulation at equilibrium and non-equilibrium positions, iv) compact design and high torque density (~36Nm/kg), and v) high-speed stiffness modulation (~3000Nm/rad/s). Such features can help boost the safety and performance of many advanced robotic systems, e.g., a cobot that physically interacts with unstructured environments and an exoskeleton that provides physical assistance to human users. These features can also enable us to utilise variable stiffness property to attain various regulation and trajectory tracking control tasks only by employing conventional controllers, eliminating the need for synthesising complex motion control systems in compliant actuation. To this end, it is experimentally demonstrated that the proposed VSSEA is capable of precisely tracking desired position and force control references through the use of conventional Proportional-Integral-Derivative (PID) controllers.

Adversarial training is an effective approach to make deep neural networks robust against adversarial attacks. Recently, different adversarial training defenses are proposed that not only maintain a high clean accuracy but also show significant robustness against popular and well studied adversarial attacks such as PGD. High adversarial robustness can also arise if an attack fails to find adversarial gradient directions, a phenomenon known as `gradient masking'. In this work, we analyse the effect of label smoothing on adversarial training as one of the potential causes of gradient masking. We then develop a guided mechanism to avoid local minima during attack optimization, leading to a novel attack dubbed Guided Projected Gradient Attack (G-PGA). Our attack approach is based on a `match and deceive' loss that finds optimal adversarial directions through guidance from a surrogate model. Our modified attack does not require random restarts, large number of attack iterations or search for an optimal step-size. Furthermore, our proposed G-PGA is generic, thus it can be combined with an ensemble attack strategy as we demonstrate for the case of Auto-Attack, leading to efficiency and convergence speed improvements. More than an effective attack, G-PGA can be used as a diagnostic tool to reveal elusive robustness due to gradient masking in adversarial defenses.

Today's software is bloated leading to significant resource wastage. This bloat is prevalent across the entire software stack, from the operating system, all the way to software backends, frontends, and web-pages. In this paper, we study how prevalent bloat is in machine learning containers. We develop MMLB, a framework to analyze bloat in machine learning containers, measuring the amount of bloat that exists on the container and package levels. Our tool quantifies the sources of bloat and removes them. We integrate our tool with vulnerability analysis tools to measure how bloat affects container vulnerabilities. We experimentally study 15 machine learning containers from the official Tensorflow, Pytorch, and NVIDIA container registries under different tasks, (i.e., training, tuning, and serving). Our findings show that machine learning containers contain bloat encompassing up to 80\% of the container size. We find that debloating machine learning containers speeds provisioning times by up to $3.7\times$ and removes up to 98\% of all vulnerabilities detected by vulnerability analysis tools such as Grype. Finally, we relate our results to the larger discussion about technical debt in machine learning systems.

We consider the problem of improving the human instance segmentation mask quality for a given test image using keypoints estimation. We compare two alternative approaches. The first approach is a test-time adaptation (TTA) method, where we allow test-time modification of the segmentation network's weights using a single unlabeled test image. In this approach, we do not assume test-time access to the labeled source dataset. More specifically, our TTA method consists of using the keypoints estimates as pseudo labels and backpropagating them to adjust the backbone weights. The second approach is a training-time generalization (TTG) method, where we permit offline access to the labeled source dataset but not the test-time modification of weights. Furthermore, we do not assume the availability of any images from or knowledge about the target domain. Our TTG method consists of augmenting the backbone features with those generated by the keypoints head and feeding the aggregate vector to the mask head. Through a comprehensive set of ablations, we evaluate both approaches and identify several factors limiting the TTA gains. In particular, we show that in the absence of a significant domain shift, TTA may hurt and TTG show only a small gain in performance, whereas for a large domain shift, TTA gains are smaller and dependent on the heuristics used, while TTG gains are larger and robust to architectural choices.

Rating a video based on its content is an important step for classifying video age categories. Movie content rating and TV show rating are the two most common rating systems established by professional committees. However, manually reviewing and evaluating scene/film content by a committee is a tedious work and it becomes increasingly difficult with the ever-growing amount of online video content. As such, a desirable solution is to use computer vision based video content analysis techniques to automate the evaluation process. In this paper, related works are summarized for action recognition, multi-modal learning, movie genre classification, and sensitive content detection in the context of content moderation and movie content rating. The project page is available at https://github.com/fcakyon/content-moderation-deep-learning}.

Generalizable 3D part segmentation is important but challenging in vision and robotics. Training deep models via conventional supervised methods requires large-scale 3D datasets with fine-grained part annotations, which are costly to collect. This paper explores an alternative way for low-shot part segmentation of 3D point clouds by leveraging a pretrained image-language model, GLIP, which achieves superior performance on open-vocabulary 2D detection. We transfer the rich knowledge from 2D to 3D through GLIP-based part detection on point cloud rendering and a novel 2D-to-3D label lifting algorithm. We also utilize multi-view 3D priors and few-shot prompt tuning to boost performance significantly. Extensive evaluation on PartNet and PartNet-Mobility datasets shows that our method enables excellent zero-shot 3D part segmentation. Our few-shot version not only outperforms existing few-shot approaches by a large margin but also achieves highly competitive results compared to the fully supervised counterpart. Furthermore, we demonstrate that our method can be directly applied to iPhone-scanned point clouds without significant domain gaps.

Animals run robustly in diverse terrain. This locomotion robustness is puzzling because axon conduction velocity is limited to a few ten meters per second. If reflex loops deliver sensory information with significant delays, one would expect a destabilizing effect on sensorimotor control. Hence, an alternative explanation describes a hierarchical structure of low-level adaptive mechanics and high-level sensorimotor control to help mitigate the effects of transmission delays. Motivated by the concept of an adaptive mechanism triggering an immediate response, we developed a tunable physical damper system. Our mechanism combines a tendon with adjustable slackness connected to a physical damper. The slack damper allows adjustment of damping force, onset timing, effective stroke, and energy dissipation. We characterize the slack damper mechanism mounted to a legged robot controlled in open-loop mode. The robot hops vertically and planar over varying terrains and perturbations. During forward hopping, slack-based damping improves faster perturbation recovery (up to 170%) at higher energetic cost (27%). The tunable slack mechanism auto-engages the damper during perturbations, leading to a perturbation-trigger damping, improving robustness at minimum energetic cost. With the results from the slack damper mechanism, we propose a new functional interpretation of animals' redundant muscle tendons as tunable dampers.