Search

Moving Object Detection (MOD) aims at extracting foreground moving objects in videos from static cameras. While low-rank based approaches have achieved impressive success in the MOD task, their performance remains limited on dynamics background scenes. The main reason is that dynamic clutters, e.g. , swaying leaves and rippers , are easy to mix up with moving objects in the decomposition model which simply classify the sparse noise as foregrounds. In order to improve the generalization ability of low-rank based moving object detectors, we suggest adding an explicit dynamic clutter component in the decomposition framework with realistic dynamic background modeling. Then the dynamic clutter can be learned through object-free video data due to their self-similarity across time and space. Thus, the moving objects can be naturally separated by a tensor-based decomposition model which formulates the static background by a unidirectional low-rank tensor, learns the dynamic clutter by a two-stream neural network, and constrains moving objects with spatiotemporal continuity. To further provide a more accurate object detection result, an objectness prior is embedded into our model in an attention manner. Extensive experimental results on the challenging datasets of dynamic background clearly demonstrate the superior performance of our model over the state-of-the-art in terms of quantitative metrics and visual quality. [Display omitted] • A novel video decomposition framework, additionally modeling the dynamic clutter explicitly. • A unified tensor-based framework to capture the appearance and motion information simultaneously for three components. • A self-supervised strategy to learn the dynamic clutter well by considering the video sequence itself as a dataset. • Bridge the gap between discriminative prior and the low-rank MAP framework. [ABSTRACT FROM AUTHOR]

While Human-Object Interaction (HOI) Detection has achieved tremendous advances in recent, it still remains challenging due to complex interactions with multiple humans and objects occurring in images, which would inevitably lead to ambiguities. Most existing methods either generate all human-object pair candidates and infer their relationships by cropped local features successively in a two-stage manner, or directly predict interaction points in a one-stage procedure. However, the lack of spatial configurations or reasoning steps of two- or one- stage methods respectively limits their performance in such complex scenes. To avoid this ambiguity, we propose a novel actor-centric framework. The main ideas are that when inferring interactions: 1) the non-local features of the entire image guided by actor position are obtained to model the relationship between the actor and context, and then 2) we use an object branch to generate pixel-wise interaction area prediction, where the interaction area denotes the object central area. Moreover, we also use an actor branch to get interaction prediction of the actor and propose a novel composition strategy based on center-point indexing to generate the final HOI prediction. Thanks to the usage of the non-local features and the partly-coupled property of the human-objects composition strategy, our proposed framework can detect HOI more accurately especially for complex images. Extensive experimental results show that our method achieves the state-of-the-art on the challenging V-COCO and HICO-DET benchmarks and is more robust especially in multiple persons and/or objects scenes. [Display omitted] • We propose a novel actor-centric HOI detection framework to explore the relationships between one human and multiple objects. • We formulate the HOI detection task as a pixel-wise classification problem in a one-stage-like procedure. • We present an RGBM Generator to provide the actor-centric guidance and get the final prediction by scoremap indexing. • Both quantitative and qualitative results prove the superiority of our method, especially for complex images. [ABSTRACT FROM AUTHOR]