Collaborating Authors

Occlusion Handling in Generic Object Detection: A Review Artificial Intelligence

The significant power of deep learning networks has led to enormous development in object detection. Over the last few years, object detector frameworks have achieved tremendous success in both accuracy and efficiency. However, their ability is far from that of human beings due to several factors, occlusion being one of them. Since occlusion can happen in various locations, scale, and ratio, it is very difficult to handle. In this paper, we address the challenges in occlusion handling in generic object detection in both outdoor and indoor scenes, then we refer to the recent works that have been carried out to overcome these challenges. Finally, we discuss some possible future directions of research.

Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark Artificial Intelligence

Tracking by natural language specification is a new rising research topic that aims at locating the target object in the video sequence based on its language description. Compared with traditional bounding box (BBox) based tracking, this setting guides object tracking with high-level semantic information, addresses the ambiguity of BBox, and links local and global search organically together. Those benefits may bring more flexible, robust and accurate tracking performance in practical scenarios. However, existing natural language initialized trackers are developed and compared on benchmark datasets proposed for tracking-by-BBox, which can't reflect the true power of tracking-by-language. In this work, we propose a new benchmark specifically dedicated to the tracking-by-language, including a large scale dataset, strong and diverse baseline methods. Specifically, we collect 2k video sequences (contains a total of 1,244,340 frames, 663 words) and split 1300/700 for the train/testing respectively. We densely annotate one sentence in English and corresponding bounding boxes of the target object for each video. We also introduce two new challenges into TNL2K for the object tracking task, i.e., adversarial samples and modality switch. A strong baseline method based on an adaptive local-global-search scheme is proposed for future works to compare. We believe this benchmark will greatly boost related researches on natural language guided tracking.

Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation Artificial Intelligence

Action segmentation refers to inferring boundaries of semantically consistent visual concepts in videos and is an important requirement for many video understanding tasks. For this and other video understanding tasks, supervised approaches have achieved encouraging performance but require a high volume of detailed frame-level annotations. We present a fully automatic and unsupervised approach for segmenting actions in a video that does not require any training. Our proposal is an effective temporally-weighted hierarchical clustering algorithm that can group semantically consistent frames of the video. Our main finding is that representing a video with a 1-nearest neighbor graph by taking into account the time progression is sufficient to form semantically and temporally consistent clusters of frames where each cluster may represent some action in the video. Additionally, we establish strong unsupervised baselines for action segmentation and show significant performance improvements over published unsupervised methods on five challenging action segmentation datasets. Our approach also outperforms weakly-supervised methods by large margins on 4 of these datasets. Interestingly, we also achieve better results than many fully-supervised methods that have reported results on these datasets. Our code is available at

VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localization Artificial Intelligence

Abstract--We present a transformer-based image anomaly detection and localization network. Our proposed model is a combination of a reconstruction-based approach and patch embedding. The use of transformer networks helps preserving the spatial information of the embedded patches, which is later processed by a Gaussian mixture density network to localize the anomalous areas. In addition, we also publish BTAD, a real-world industrial anomaly dataset. Our results are compared with other state-of-the-art algorithms using publicly available datasets like MNIST and MVTec.

One year later, Bixby is still half-baked


Now that the Galaxy S9 and S9 Plus are on sale, I thought we should take some time to get reacquainted with Samsung's ambitious virtual assistant. The sad truth is, the version of Bixby installed on the Galaxy S9 and S9 Plus isn't that much better than what shipped on last year's Samsung flagships. Bixby does a lot of things, but some of Samsung's most fascinating work has gone into Bixby Vision, a suite of seemingly useful image recognition tools. Here's the rub, though: They're just about all powered by third-party services, and there's often little reason to use Bixby over any of those standalone apps. Vision is legitimately useful in that it provides a single place to access these functions, but it's hard to get excited when Samsung's main selling point comes down to convenience.