41 accepted papers
Drag-driven editing has become popular among designers for its ability to modify complex geometric structures through simple and intuitive manipulation, allowing users to adjust and reshape content with minimal technical skill. This drag operation has been incorporated into numerous methods to facil…
Complex dynamic scenes present significant challenges for predicting human behavior due to the abundance of interaction information, such as human-human and human-environment interactions. These factors complicate the analysis and understanding of human behavior, thereby increasing the uncertainty i…
Reference-to-video (R2V) generation aims to synthesize videos that align with a text prompt while preserving the subject identity from reference images. However, current R2V methods are hindered by the reliance on explicit reference image-video-text triplets, whose construction is highly expensive a
Unified multimodal models (UMMs) aim to jointly perform multimodal understanding and generation within a single framework. We present TUNA, a native UMM that builds a unified continuous visual representation by cascading a VAE encoder with a representation encoder. This unified representation space
This paper presents a theoretical investigation into the generalization capabilities of cross-domain knowledge distillation. Utilizing a high-dimensional asymptotic analysis of a linear teacher–student model, we characterize the excess risk while accounting for both model and covariate shifts. Our r…
Recent advances in tool-integrated language agents have significantly improved their ability to solve complex reasoning tasks. However, existing alignment methods predominantly focus on maximizing task accuracy, while overlooking auxiliary objectives such as tool-use efficiency, which are essential …
Vector glyphs are the atomic units of digital typography, yet most learning-based pipelines still depend on carefully curated exemplar sheets and raster-to-vector postprocessing, which limits accessibility and editability. We introduce VecGlypher, a single multimodal language model that generates hi
Recent research showcases the considerable potential of conditional diffusion models for generating consistent stories. However, current methods, which primarily generate stories in a caption-dependent manner, often overlook the importance of contextual consistency and the relevance of frames durin…
Recent advancements in Large Language Models (LLMs) have emphasized the critical role of fine-tuning (FT) techniques in adapting LLMs to specific tasks, especially when retraining from scratch is computationally infeasible. Fine-tuning enables LLMs to leverage task- or domain-specific data, producin…
In this paper, we investigate deep feedforward neural networks with random weights. The input data matrix $\boldsymbol{X}$ is drawn from a Gaussian mixture model. We demonstrate that certain eigenvalues of the conjugate kernel and neural tangent kernel may lie outside the support of their limiting s…
As urban residents demand higher travel quality, vehicle dispatch has become a critical component of online ride-hailing services. However, current vehicle dispatch systems struggle to navigate the complexities of urban traffic dynamics, including unpredictable traffic conditions, diverse driver beh…
Controllable person image generation aims to generate a person image conditioned on reference images, allowing precise control over the person's appearance or pose.However, prior methods often distort fine-grained textural details from the reference image, despite achieving high overall image qualit…
Spatio-temporal graph modeling is widely applied to spatio-temporal data, analyzing the relationships between data to achieve accurate predictions. However, despite the excellent predictive performance of increasingly complex models, their intricate architectures result in significant memory overhea
Identifying the root causes of anomalies in multivariate time series is challenging due to the complex dependencies among the series. In this paper, we propose a comprehensive approach called AERCA that inherently integrates Granger causal discovery with root cause analysis. By defining anomalies as…
We present StdGEN, an innovative pipeline for generating semantically decomposed high-quality 3D characters from single images, enabling broad applications in virtual reality, gaming, and filmmaking, etc. Unlike previous methods which struggle with limited decomposability, unsatisfactory quality, an…
Human-centric Point Cloud Video Understanding (PVU) is an emerging field focused on extracting and interpreting human-related features from sequences of human point clouds further advancing downstream human-centric tasks and applications. Previous works usually focus on tackling one specific task an…
Recent work has showcased the significant potential of diffusion models in pose-guided person image synthesis. However, owing to the inconsistency in pose between the source and target images, synthesizing an image with a distinct pose, relying exclusively on the source image and target pose informa…
Worldwide geolocalization aims to locate the precise location at the coordinate level of photos taken anywhere on the Earth. It is very challenging due to 1) the difficulty of capturing subtle location-aware visual semantics, and 2) the heterogeneous geographical distribution of image data. As a res…
Pre-travel recommendation is developed to provide a variety of out-of-town Point-of-Interests (POIs) for users planning to travel away from their hometowns but have not yet decided on their destination. Existing out-of-town recommender systems work on constructing users' latent preferences and infer…
Reinforcement learning with natural language action space often suffers from the curse of dimensionality due to the combinatorial nature of the natural language. Previous research leverages pretrained language models to capture action semantics and reduce the size of the action space. However, since…
"LiDAR-based human motion capture has garnered significant interest in recent years for its practicability in large-scale and unconstrained environments. However, most methods rely on cleanly segmented human point clouds as input, the accuracy and smoothness of their motion results are compromised w…
For human-centric large-scale scenes fine-grained modeling for 3D human global pose and shape is significant for scene understanding and can benefit many real-world applications. In this paper we present LiveHPS a novel single-LiDAR-based approach for scene-level human pose and shape estimation with…
The effectiveness of large language models (LLMs) is often hindered by duplicated data in their extensive pre-training datasets. Current approaches primarily focus on detecting and removing duplicates, which risks the loss of valuable information and neglects the varying degrees of duplication. To a…
The integration of visual encoders and large language models (LLMs) has driven recent progress in multimodal large language models (MLLMs). However, the scarcity of high-quality instruction-tuning data for vision-language tasks remains a challenge. The current leading paradigm, such as LLaVA, relies…
Creating stable, controllable videos is a complex task due to the need for significant variation in temporal dynamics and cross-frame temporal consistency. To address this, we enhance the spatial-temporal capability and introduce a versatile video generation model, VersVideo, which leverages textual…
By focusing the pre-training process on domain-specific corpora, some domain-specific pre-trained language models (PLMs) have achieved state-of-the-art results. However, it is under-investigated to design a unified paradigm to inject domain knowledge in the PLM fine-tuning stage. We propose Knowledg…
Controllable person image synthesis aims at rendering a source image based on user-specified changes in body pose or appearance. Prior art approaches leverage pixel-level denoising diffusion models conditioned on the coarse skeleton via cross-attention. This leads to two limitations: low efficiency…
In the fashion domain, there exists a variety of vision-and-language (V+L) tasks, including cross-modal retrieval, text-guided image retrieval, multi-modal classification, and image captioning. They differ drastically in each individual input/output format and dataset size. It has been common to des…
Recently, text-guided 3D generative methods have made remarkable advancements in producing high-quality textures and geometry, capitalizing on the proliferation of large vision-language and image diffusion models. However, existing methods still struggle to create high-fidelity 3D head avatars in t…
Personalized federated learning (pFL) collaboratively trains personalized models, which provides a customized model solution for individual clients in the presence of heterogeneous distributed local data. Although many recent studies have applied various algorithms to enhance personalization in pFL,…
Whole-slide images (WSI) in computational pathology have high resolution with gigapixel size, but are generally with sparse regions of interest, which leads to weak diagnostic relevance and data inefficiency for each area in the slide. Most of the existing methods rely on a multiple instance learnin…
Accurate perception of objects in the environment is important for improving the scene understanding capability of SLAM systems. In robotic and augmented reality applications, object maps with semantic and metric information show attractive advantages. In this letter, we present RO-MAP, a novel mult
"Large-scale Vision-and-Language (V+L) pre-training for representation learning has proven to be effective in boosting various downstream V+L tasks. However, when it comes to the fashion domain, existing V+L methods are inadequate as they overlook the unique characteristics of both fashion V+L data…
The large-scale whole-slide images (WSIs) facilitate the learning-based computational pathology methods. However, the gigapixel size of WSIs makes it hard to train a conventional model directly. Current approaches typically adopt multiple-instance learning (MIL) to tackle this problem. Among them, M…
Bilingual lexicon induction induces the word translations by aligning independently trained word embeddings in two languages. Existing approaches generally focus on minimizing the distances between words in the aligned pairs, while suffering from low discriminative capability to distinguish the rela…
Weakly-supervised whole-slide image (WSI) classification (WSWC) is a challenging task where a large number of unlabeled patches (instances) exist within each WSI (bag) while only a slide label is given. Despite recent progress for the multiple instance learning (MIL)-based WSI analysis, the major l…
The immunohistochemistry (IHC) test of biopsy tissue is crucial to develop targeted treatment and evaluate prognosis for cancer patients. The IHC staining slide is usually digitized into the whole-slide image (WSI) with gigapixels for quantitative image analysis. To perform a whole image prediction…
Representing the true label as one-hot vector is the common practice in training text classification models. However, the one-hot representation may not adequately reflect the relation between the instance and labels, as labels are often not completely independent and instances may relate to multipl…
Recently, sponsored search has become one of the most lucrative channels for marketing. As the fundamental basis of sponsored search, relevance modeling has attracted increasing attention due to the tremendous practical value. Most existing methods solely rely on the query-keyword pairs. However, ke…
Nucleus instance segmentation and classification in histopathological images is an essential prerequisite in pathology diagnosis/prognosis. However, nucleus annotations (e.g., segmentation and labeling) require domain experts, and annotating nuclei at pixel-level is time-consuming and labor-intensiv…
Weakly supervised semantic segmentation with image-level labels has attracted a lot of attention recently because these labels are already available in most datasets. To obtain semantic segmentation under weak supervision, this paper presents a simple yet effective approach based on the idea of expl…