Search Results

Although multi-view human pose and shape regression methods have information from other views for complementing and correcting, existing ones still have its own drawback of not fully taking advantage of multi-view setup. Thus they are far from ...

• A new network for multi-view human pose and shape regression.
• Human body features are well merged through multi-scale volumetric aggregation.
• A mesh-aligned voxel selection module is proposed to make effective prediction.
• A new ...

Long-term user behavior sequences are a goldmine for businesses to explore users’ interests to improve Click-Through Rate (CTR). However, it is very challenging to accurately capture users’ long-term interests from their long-term behavior ...

Today's scene graph generation (SGG) models typically require abundant manual annotations to learn new predicate types. Therefore, it is difficult to apply them to real-world applications with massive uncommon predicate categories whose annotations are ...

Interactive Video Object Segmentation (iVOS) is inherently demanding, requiring real-time interaction between humans and computers. Enhancing user experience involves considerations such as user input habits, segmentation quality, running time, and memory ...

Distinctive Image Captioning (DIC)—generating distinctive captions that describe the unique details of a target image—has received considerable attention over the last few years. A recent DIC method proposes to generate distinctive captions by comparing ...

Previous weakly-supervised object localization (WSOL) methods aim to expand activation map discriminative areas to cover the whole objects, yet neglect two inherent challenges when relying solely on image-level labels. First, the “entangled context&...

The technique of 3D Gaussian splatting (3DGS) has demonstrated its effectiveness and efficiency in rendering photo-realistic images for novel view synthesis. However, 3DGS requires a high density of camera coverage, and its performance inevitably ...

Benefiting from strong generalization ability, pre-trained vision-language models (VLMs), e.g., CLIP, have been widely utilized in zero-shot scene understanding. Unlike simple recognition tasks, grounded situation recognition (GSR) requires the model not ...

4D facial expression synthesizing is a critical problem in the fields of computer vision and graphics. Current methods lack flexibility and smoothness when simulating the inter-frame motion of expression sequences. In this paper, we propose a frequency-...

Maintaining temporal stability is crucial in multi-agent trajectory prediction. Insufficient regularization to uphold this temporal stability often results in fluctuations in kinematic states, leading to inconsistent predictions and the amplification of ...

Nearly all existing scene graph generation (SGG) models have overlooked the ground-truth annotation qualities of mainstream SGG datasets, i.e., they assume: 1) all the manually annotated positive samples are equally correct; 2) all the un-annotated ...

Existing imaging systems support wide-gamut images like ProPhoto RGB, but most images are typically encoded in a narrower gamut space (e.g., sRGB). To this end, these images can be enhanced by learning to recover the original color values beyond ...$\mathcal{}\mathrm{}$

Explicit Caption Editing (ECE)—refining reference image captions through a sequence of explicit edit operations (e.g., KEEP, DETELE)—has raised significant attention due to its explainable and human-like nature. After training with carefully ...

Transformer has become the de-facto architecture for many natural language and vision tasks thanks to its remarkable performance. As an essential part of transformers, normalization functions struggle to improve the robustness and performance of ...

Single image super-resolution is a classic problem in computer vision. In recent years, deep learning-based models have achieved unprecedented success with this problem. However, most existing deep super-resolution models unavoidably produce ...

• This paper focuses on a real-world degradation, i.e., the multiple-focal-length degradation, for single image super-resolution.
• An efficient multi-scale feature mixture model is proposed for restoring images under the multiple-focal-...

Skin tumors are the most common tumors in humans and the clinical characteristics of three common non-melanoma tumors (IDN, SK, BCC) are similar, resulting in a high misdiagnosis rate. The accurate differential diagnosis of these tumors needs to ...

• We develop a publicly available skin pathological image dataset, SPMLD, carried out by some dermatologists who collect and annotate the dataset.
• We propose a lesion area-based enhanced classification network, which can automatically ...

Panoptic Scene Graph Generation (PSG) aims to generate a comprehensive graph-structure representation based on panoptic segmentation masks. Despite remarkable progress in PSG, almost all existing methods neglect the importance of shape-aware ...

To propose a single-stage object detection method for realizing real-time and accurate identification and detection of near-ground small pothole objects photographed by UAV. Through the special copy-paste technology of the pothole dataset obtained ...

In this work, we introduce a controlled dynamic vector graphic generation method. While existing work mostly focuses on text-based generation of single-frame images, dynamic images, or single-frame vectors, there is a lack of research on generating ...

Controllable Image Captioning (CIC)—generating natural language descriptions about images under the guidance of given control signals—is one of the most promising directions toward next-generation captioning systems. Till now, various kinds of ...