51 accepted papers
Controllable hand image generation aims to synthesize geometrically accurate images with consistent appearance. Recently, diffusion models have been widely applied for hand image synthesis. However, through input-level fusion or feature-level modulation, existing methods inject control signals with
With the rise of pre-trained vision-language models such as CLIP, performing video anomaly detection (VAD) through cross-modal reasoning has become an emerging trend. However, we observe that CLIP still suffers from weak abnormality awareness: normal and abnormal descriptions are highly entangled in
Cross-tokenizer knowledge distillation, where the teacher and student employ different tokenizers, is becoming increasingly prevalent, yet it poses underexplored challenges: existing methods fail to capture the rich knowledge encoded in teacher logits, as evidenced by the neglect of semantic informa
Understanding interacting hand-object from monocular videos is crucial for immersive and dexterous interactions in AR/VR and robotic applications. However, existing monocular reconstruction methods primarily assume rigid grasping and static object geometry. When applied to articulated manipulations,
In this paper, we explore video anomaly detection (VAD) from a fine-grained perspective, which aims not only to detect anomalous events but also to identify their specific categories. Due to the limited number of examples per category, existing methods either fail to handle intra-class variation acr
Deep learning approaches typically require prohibitive amounts of data to approximate strict Exact Cover Problems, while existing neuro-symbolic methods often face training infeasibility and scalability bottlenecks. To bridge this divide, we propose the Hypergraph Optimization Network (HONet), an en…
Diffusion models have achieved remarkable success in graph generation, but enforcing hard constraints on generated graphs remains challenging, limiting their deployment in constraint-critical applications. Existing approaches either fail to guarantee strict constraint satisfaction or are limited to …
Low-Rank Adaptation (LoRA) is a popular approach that enables large language models (LLMs) to quickly adapt to domain-specific tasks by adding lightweight trainable adapters. Existing multi-LoRA serving systems typically exploit parameter sharing to serve hundreds of LoRA models with a single base m
By providing a standardized interface for LLM agents to interact with external tools, the Model Context Protocol (MCP) is quickly becoming a cornerstone of the modern autonomous agent ecosystem. However, it creates novel attack surfaces due to untrusted external tools. While prior work has focused o
Existing machine learning models for network simulation excel at predicting average performance but, due to their reliance on mean squared error, systematically fail to capture the critical tail-latency and jitter that define modern network stability. This 'tail-blindness' renders them unreliable fo…
Precise 3D hand posture is essential for learning musical instruments. Reconstructing highly precise 3D hand gestures enables learners to correct and master proper techniques through 3D simulation and Extended Reality. However, exsiting methods typically rely on precisely calibrated multi-camera sys
Accurate forecasting of time series is crucial for many applications in the real world. Conventional methods primarily rely on statistical analysis of historical data, often leading to overfitting and failing to account for background information and constraints imposed by external events. Therefore
Human experts typically integrate numerical and textual multimodal information to analyze time series. However, most traditional deep learning predictors rely solely on unimodal numerical data, using a fixed-length window for training and prediction on a single dataset, and cannot adapt to different…
Sparse attention can effectively alleviate the significant demands on memory when large language models (LLMs) process long contexts. Existing methods typically apply the same sparse pattern across different attention heads and inputs. However, this uniform approach fails to capture the inherent div…
Temporal sentence grounding in videos (TSGV) faces challenges due to public TSGV datasets containing significant temporal biases, which are attributed to the uneven temporal distributions of target moments. Existing methods generate augmented videos, where target moments are forced to have varying t…
Large Vision-Language Models (LVLMs) pretrained on large-scale multimodal data have shown promising capabilities in Video Anomaly Detection (VAD). However, their ability to reason about abnormal events based on scene semantics remains underexplored. In this paper, we investigate LVLMs’ behavior in V…
Deep learning-based recommendation systems are increasingly important in the industry. To meet strict SLA requirements, serving frameworks must efficiently handle concurrent queries. However, current serving systems fail to serve concurrent queries due to the following problems: (1) inefficient oper
Large Vision-Language Models (LVLMs) have a significant issue with object hallucinations, where researchers have noted that LVLMs often mistakenly determine objects as present in images where they do not actually exist. Some recent studies evaluate the occurrence of object hallucinations by asking L…
Recent advances in hand-object interaction modeling have employed implicit representations, such as Signed Distance Functions (SDF) and Neural Radiance Fields (NeRF) to reconstruct hands and objects with arbitrary topology and photo-realistic detail. However, these methods often rely on dense 3D sur…
3D hand reconstruction is essential in non-contact human-computer interaction applications, but existing methods struggle with low-resolution images, which occur in slightly distant interactive scenes. Leveraging temporal information can mitigate the limitations of individual low-resolution images t…
3D hand pose estimation plays a critical role in various human-computer interaction tasks. Single-frame 3D hand pose estimation methods have poor temporal smoothness and are easily affected by self-occlusion, which severely impacts their practical applicability. Traditional joint-based sequential po…
Large language models (LLMs) have demonstrated outstanding performance in various tasks. However, the memory footprint of the key-value (KV) cache generated during model inference poses significant challenges for efficient model deployment. This paper presents a detailed analysis of the KV cache and…
Recommendation Models (RMs) are crucial for predicting user preferences and enhancing personalized experiences on large-scale platforms. As the application of recommendation models grows, optimizing their online serving performance has become a significant challenge. However, current serving systems…
Entity alignment (EA) is crucial for integrating multi-source knowledge graphs (KGs), aiming to identify equivalent entities across different graphs. However, most existing EA decoding methods rely on both entity and relation embeddings, limiting their generalizability and efficiency, especially in…
Prompts, especially high-quality ones, play an invaluable role in assisting large language models (LLMs) to accomplish various natural language processing tasks. However, carefully crafted prompts can also manipulate model behavior. Therefore, the security risks that “prompts themselves face” and th…
Multi-view 3D human pose estimation (HPE) leverages complementary information across views to improve accuracy and robustness. Traditional methods rely on camera calibration to establish geometric correspondences, which is sensitive to calibration accuracy and lacks flexibility in dynamic settings.…
Existing research in multi-hop questions has identified two reasoning modes: latent reasoning and factual shortcuts, but has not deeply investigated how these modes differ during inference. This impacts both model generalization ability and downstream reasoning tasks. In this work, we systematically
"Recent research has explored implicit representations, such as signed distance function (SDF), for interacting hand-object reconstruction. SDF enables modeling hand-held objects with arbitrary topology and overcomes the resolution limitations of parametric models, allowing for finer-grained reconst…
Code summarization provides a natural language description for a given piece of code. In this work, we focus on scripting code—programming languages that interact with specific devices through commands. The low-resource nature of scripting languages makes traditional code summarization methods chall…
Pre-trained foundation models, particularly large language models, have achieved remarkable success and led to massive fine-tuned variants. These models are commonly fine-tuned locally and then uploaded by users to cloud platforms such as HuggingFace for secure storage. However, the huge model numbe…
Micro-enterprises and individual developers emerge analysis demands for long sequence with powerful Large Language Models (LLMs). They try to deploy the LLMs at local, but only possess various commodity devices and the unreliable interconnection between devices. Existing parallel techniques do not l…
Previous 3D hand pose estimation methods primarily rely on a single modality, either RGB or depth, and the comprehensive utilization of the dual modalities has not been extensively explored. RGB and depth data provide complementary information and thus can be fused to enhance the robustness of 3D ha…
Recently, retrieval-based in-context learning (ICL) methods for selecting demonstrations have been widely investigated. Existing methods train a dense retriever to retrieve the most appropriate demonstrations for a given test query, which improves ICL performance. However, we find that distinct LLMs…
ecent progress in video anomaly detection suggests that the features of appearance and motion play crucial roles in distinguishing abnormal patterns from normal ones. However we note that the effect of spatial scales of anomalies is ignored. The fact that many abnormal events occur in limited locali…
Time series forecasting has played a pivotal role across various industries, including finance, transportation, energy, healthcare, and climate. Due to the abundant seasonal information they contain, timestamps possess the potential to offer robust global guidance for forecasting techniques. However…
Language Models (LMs) acquire factual knowledge during pre-training and store it in the parameters, which can be valuable for downstream tasks. As world evolves, some facts may be incorrectly induced or become obsolete over time. Various model editing methods have been proposed to modify specific ex…
Sustainable cities requires high-quality community management and surveillance analytics, which are supported by video anomaly detection techniques. However, mainstream video anomaly detection techniques still require manually labeled data and do not apply to real-world massive videos. Without label…
Reconstructing interacting hands from a single RGB image is a very challenging task. On the one hand, severe mutual occlusion and similar local appearance between two hands confuse the extraction of visual features, resulting in the misalignment of estimated hand meshes and the image. On the other h…
Many unsupervised methods have recently been proposed for multivariate time series anomaly detection. However, existing works mainly focus on stable data yet often omit the drift generated from non-stationary environments, which may lead to numerous false alarms. We propose **D**ynamic **D**ecomposi…
Fake news causes cognitive misperception among the audience and spreads panic to the public. It is crucial to detect fake news and prevent its spread early. Previous methods focus on excavating distinguishable features from news contents in a single domain with deep models, which are difficult to ge…
Recent graph-based methods achieve significant success in multivariate time series modeling and forecasting due to their ability to handle relationships among time series variables. However, only pairwise relationships are considered in most existing works. They ignore beyond-pairwise relationships…
Video anomaly detection aims to automatically detect abnormal objects or behaviors. Most existing methods tackle the problem by minimizing the reconstruction errors stemming from the lack of anomalous data, which leads to poor interpretability and robustness. Focus on the context-dependent nature of…
RGB and depth modalities provide complementary information, which can be effectively utilized to improve the performance of hand detection in the wild. Most existing fusion-based methods model the channel-wise or spatial-wise cross-modal correlation to exploit the complementary RGB-D information, in…
The sketch-based image retrieval (SBIR) task has long been researched at the instance level, where both query sketches and candidate images are assumed to contain only one dominant object. This strong assumption constrains its application, especially with the increasingly popular intelligent termina…
Sketch-based image retrieval (SBIR) is an attractive research area where freehand sketches are used as queries to retrieve relevant images. Existing solutions have advanced the task to the challenging zero-shot setting (ZS-SBIR), where the trained models are tested on new classes without seen data.…
Depth images and point clouds are the two most commonly used data representations for depth-based 3D hand pose estimation. Benefiting from the structuring of image data and the inherent inductive biases of the 2D Convolutional Neural Network (CNN), image-based methods are highly efficient and effect…
"Temporal grounding aims to locate a target video moment that semantically corresponds to the given sentence query in an untrimmed video. However, recent works find that existing methods suffer a severe temporal bias problem. These methods do not reason the target moment locations based on the visua…
In this work, we study the cross-view information fusion problem in the task of self-supervised 3D hand pose estimation from the depth image. Previous methods usually adopt a hand-crafted rule to generate pseudo labels from multi-view estimations in order to supervise the network training in each vi…
Aspect-based sentiment analysis (ABSA) aims to distinguish sentiment polarity of every specific aspect in a given sentence. Previous researches have realized the importance of interactive learning with context and aspects. However, these methods are ill-studied to learn complex sentence with multipl…
The data sparsity is the main challenge in sentence classification in social scenarios, the recent methods incorporate user information by encoding user node in the user-relation network to alleviate this issue. However, the connection between users is not always available due to privacy protection…
Channel pruning can significantly accelerate and compress deep neural networks. Many channel pruning works utilize structured sparsity regularization to zero out all the weights in some channels and automatically obtain structure-sparse network in training stage. However, these methods apply structu…