Most existing methods realize 3D instance segmentation by extending those models used for object detection or semantic segmentation. However, these non-straightforward suffer from two drawbacks: 1) Imprecise bounding boxes unsatisfactory predictions limit the performance of overall framework. 2) Existing method requires a time-consuming intermediate step aggregation. To address issues, this pap...

With the continuous development of network technology, an intrusion detection system needs to face efficiency and storage requirement when dealing with large data. A reasonable way alleviating this problem is instance selection, which can reduce space improve by selecting representative instances. An not only in its class but also different classes. This representativeness reflects importance i...

Referring segmentation aims to generate a mask for the target instance indicated by natural language expression. There are typically two kinds of existing methods: one-stage methods that directly perform on fused vision and features; two-stage first utilize an model proposal then select one these instances via matching them with features. In this work, we propose novel framework simultaneously ...

In this work, we present SeqFormer for video instance segmentation. follows the principle of vision transformer that models relationships among frames. Nevertheless, observe a stand-alone query suffices capturing time sequence instances in video, but attention mechanisms shall be done with each frame independently. To achieve this, locates an and aggregates temporal information to learn powerfu...

We propose a multi-cue based approach for recognizing human actions in still images, where relevant object regions are discovered and utilized in a weakly supervised manner. Our approach does not require any explicitly trained object detector or part/attribute annotation. Instead, a multiple instance learning approach is used over sets of object hypotheses in order to represent objects relevant...

Multi-Instance Learning (MIL) deals with problems where each training example is a bag, and each bag contains a set of instances. Multi-instance representation is useful in many real world applications, because it is able to capture more structural information than traditional flat single-instance representation. However, it also brings new challenges. Specifically, the distance between data ob...

We present a new multiple-instance (MI) learning technique (EMDD) that combines EM with the diverse density (DD) algorithm. EM-DD is a general-purpose MI algorithm that can be applied with boolean or real-value labels and makes real-value predictions. On the boolean Musk benchmarks, the EM-DD algorithm without any tuning significantly outperforms all previous algorithms. EM-DD is relatively ins...