9 accepted papers
Contemporary recommendation systems predominantly rely on ID embedding to capture latent associations among users and items. However, this approach overlooks the wealth of semantic information embedded within textual descriptions of items, leading to suboptimal performance and poor generalizations.…
We introduce Orthus, a unified multimodal model that excels in generating interleaved images and text from mixed-modality inputs by simultaneously handling discrete text tokens and continuous image features under the \textbf{AR} modeling principle. The continuous treatment of visual signals minimize…
This paper presents the Semantic-aWarE spatial-tEmporal Tokenizer (SweetTok), a novel video tokenizer to overcome the limitations in current video tokenization methods for compacted yet effective discretization. Unlike previous approaches that process flattened local visual patches via direct discre…
Human-centric visual tasks have attracted increasing research attention due to their widespread applications. In this paper, we aim to learn a general human representation from massive unlabeled human images which can benefit downstream human-centric tasks to the maximum extent. We call this method…
Video instance segmentation (VIS) aims at segmenting and tracking objects in videos. Prior methods typically generate frame-level or clip-level object instances first and then associate them by either additional tracking heads or complex instance matching algorithms. This explicit instance associati…
Although various methods have been proposed for pedestrian attribute recognition, most studies follow the same feature learning mechanism, ie, learning a shared pedestrian image feature to classify multiple attributes. However, this mechanism leads to low-confidence predictions and non-robustness of…
This paper presents a unified framework for depth-aware panoptic segmentation (DPS), which aims to reconstruct 3D scene with instance-level semantics from one single image. Prior works address this problem by simply adding a dense depth regression head to panoptic segmentation (PS) networks, resulti…
Video object detection has been an important yet challenging topic in computer vision. Traditional methods mainly focus on designing the image-level or box-level feature propagation strategies to exploit temporal information. This paper argues that with a more effective and efficient feature propaga…
While recent studies on pedestrian attribute recognition have shown remarkable progress in leveraging complicated networks and attention mechanisms, most of them neglect the inter-image relations and an important prior: spatial consistency and semantic consistency of attributes under surveillance sc…