Decode-MOT: How Can We Hurdle Frames to Go Beyond Tracking-by-Detection?

The speed of tracking-by-detection (TBD) greatly depends on the number of running a detector because the detection is the most expensive operation in TBD. In many practical cases, multi-object tracking (MOT) can be, however, achieved based tracking-by-motion (TBM) only. This is a possible solution without much loss of MOT accuracy when the variations of object cardinality and motions are not much within consecutive frames.

Deformable Part Region Learning and Feature Aggregation Tree Representation for Object Detection.

Region-based object detection infers object regions for one or more categories in an image. Due to the recent advances in deep learning and region proposal methods, object detectors based on convolutional neural networks (CNNs) have been flourishing and provided promising detection results. However, the accuracy of the convolutional object detectors can be degraded often due to the low feature discriminability caused by geometric variation or transformation of an object.

Effective Multi-Object Tracking via Global Object Models and Object Constraint Learning.

Effective multi-object tracking is still challenging due to the trade-off between tracking accuracy and speed. Because the recent multi-object tracking (MOT) methods leverage object appearance and motion models so as to associate detections between consecutive frames, the key for effective multi-object tracking is to reduce the computational complexity of learning both models. To this end, this work proposes global appearance and motion models to discriminate multiple objects instead of learning local object-specific models.

Electrical Transport and Thermoelectric Properties of SnSe-SnTe Solid Solution.

SnSe is considered as a promising thermoelectric (TE) material since the discovery of the record figure of merit (ZT) of 2.6 at 926 K in single crystal SnSe. It is, however, difficult to use single crystal SnSe for practical applications due to the poor mechanical properties and the difficulty and cost of fabricating a single crystal.

Confidence-Based Data Association and Discriminative Deep Appearance Learning for Robust Online Multi-Object Tracking.

Online multi-object tracking aims at estimating the tracks of multiple objects instantly with each incoming frame and the information provided up to the moment. It still remains a difficult problem in complex scenes, because of the large ambiguity in associating multiple objects in consecutive frames and the low discriminability between objects appearances. In this paper, we propose a robust online multi-object tracking method that can handle these difficulties effectively.

Debridement and Functional Rehabilitation for Achilles Tendon Infection Following Tendon Repair.

Background: An infected Achilles tendon after tendon repair is particularly difficult to treat because of the poor vascularity of the tendon as well as the thin surrounding soft tissue. For treatment of an infected Achilles tendon following tendon repair, we first focused on complete debridement and then promoted fibrous scar healing of the Achilles tendon using functional treatment.

Methods: We retrospectively reviewed all of the medical records of 15 tertiary referral patients with postoperative infection of the Achilles tendon occurring between 2007 and 2012.

Polyp Detection via Imbalanced Learning and Discriminative Feature Learning.

Recent achievement of the learning-based classification leads to the noticeable performance improvement in automatic polyp detection. Here, building large good datasets is very crucial for learning a reliable detector. However, it is practically challenging due to the diversity of polyp types, expensive inspection, and labor-intensive labeling tasks.

Robust online multiobject tracking with data association and track management.

In this paper, we consider a multiobject tracking problem in complex scenes. Unlike batch tracking systems using detections of the entire sequence, we propose a novel online multiobject tracking system in order to build tracks sequentially using online provided detections. To track objects robustly even under frequent occlusions, the proposed system consists of three main parts: 1) visual tracking with a novel data association with a track existence probability by associating online detections with the corresponding tracks under partial occlusions; 2) track management to associate terminated tracks for linking tracks fragmented by long-term occlusions; and 3) online model learning to generate discriminative appearance models for successful associations in other two parts.