United States

Text-to-image generation models have achieved remarkable advancements in recent years, aiming to produce realistic images from textual descriptions. However, these models often struggle with generating anatomically accurate representations of human hands. The resulting images frequently exhibit issues such as incorrect numbers of fingers, unnatural twisting or interlacing of fingers, or blurred and indistinct hands. These issues stem from the inherent complexity of hand structures and the difficulty in aligning textual descriptions with precise visual depictions of hands. To address these challenges,  we propose a novel approach named Hand1000 that enables the generation of realistic hand images with target gesture using only 1,000 training samples. The training of Hand1000 is divided into three stages with the first stage aiming to enhance the model’s understanding of hand anatomy by using a pre-trained hand gesture recognition model to extract gesture representation. The second stage further optimizes text embedding by incorporating the extracted hand gesture representation, to improve alignment between the textual descriptions and the generated hand images. The third stage utilizes the optimized embedding to fine-tune the Stable Diffusion model to generate realistic hand images. In addition, we construct the first publicly available dataset specifically designed for text-to-hand image generation. Based on the existing hand gesture recognition dataset, we adopt advanced image captioning models and LLaMA3 to generate high-quality textual descriptions enriched with detailed gesture information. Extensive experiments demonstrate that Hand1000 significantly outperforms existing models in producing anatomically correct hand images while faithfully representing other details in the text, such as faces, clothing and colors.

AAAI 2025

Hand1000: Generating Realistic Hands from Text with Only 1,000 Images

language and vision

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

AAAI 2021

poster

We are pleased to announce the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), which will be held in Philadelphia, Pennsylvania at the Pennsylvania Convention Center from February 25 to March 4, 2025.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

### [Invited Speakers](https://aaai.org/conference/aaai/aaai-25/aaai-25-invited-speakers/)

Register [here](https://aaai.org/conference/aaai/aaai-25/registration/)

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.



As deep learning techniques advance rapidly, deepfake speech synthesized through text-to-speech or voice conversion networks is becoming increasingly realistic, posing significant challenges for detection and raising potential threats to social security. This growing realism has prompted extensive research in speech deepfake detection. However, current detection methods primarily focus on extracting features from either the raw waveform or the spectrogram, often overlooking the valuable correspondences between these two modalities that could enhance the detection of previously unseen types of deepfakes. In this work, we propose a multi-view collaborative learning network for speech deepfake detection, which jointly learns robust speech representations from both raw waveforms and spectrograms. 
Specifically, we first design a Dual-Branch Contrastive Learning (DBCL) framework for learning different view features. DBCL consists of two branches that learn representations from the raw waveform or the spectrogram and utilizes contrastive learning to enhance inter- and inner-view correlations. Additionally, we introduce a Waveform-Spectrogram Fusion Module (WSFM) to exchange multi-view information for collaborative learning. In the feature learning process, WSFM converts features between views and merges them adaptively using waveform-spectrogram cross-attention. The final detection is conducted based on the concatenation of the waveform and spectrogram features. We conduct extensive experiments on four benchmark deepfake speech detection datasets, and the experimental results demonstrate that our method can achieve better detection performance than current state-of-the-art detection methods.

Multi-View Collaborative Learning Network for Speech Deepfake Detection

Generative models are widely used to produce synthetic images with annotations, alleviating the burden of image collection and annotation for training deep visual models. However, challenges such as limited image diversity, noisy pseudo labels, and domain gaps between synthetic and real images often undermine their effectiveness in downstream visual tasks. This paper introduces the Iterative Self-Training with Class-Aware Text-to-Image Synthesis (IST-CATS) framework, which addresses these challenges by integrating a class-aware text-to-image synthesis (CATS) component with an iterative self-training (IST) strategy. CATS innovatively introduces a class-aware chain approach to generate detailed descriptions. These descriptions act as prompts for a diffusion model, enabling the creation of a diverse of images accompanied by distinguishable objects against the background. The generated images can be easily pseudo-labeled by an unsupervised instance segmentation method and then effectively purify noisy pseudo labels by a novel feature similarity based filtering mechanism. The generated images underpin our IST, which progressively enhances vision models and refines pseudo labels through self-training and our proposed label filtering strategy (LabFilt). LabFilt meticulously improves the quality of pseudo labels by employing class-adaptive techniques at both the pixel and object levels, ensuring refined pseudo-label accuracy. IST-CATS demonstrates superior performance in object detection and semantic segmentation compared to traditional synthetic and semi/weakly-supervised methods, effectively addressing data collection and annotation challenges.

Iterative Self-Training with Class-Aware Text-to-Image Synthesis for Visual Task Learning

Segment Anything Model (SAM) has made great progress in anomaly segmentation tasks due to its impressive generalization ability. However, existing methods that directly apply SAM through prompting often overlook the domain shift issue, where SAM performs well on natural images but struggles in industrial scenarios. Parameter-Efficient Fine-Tuning (PEFT) offers a promising solution, but it may yield suboptimal performance by not adequately addressing the perception challenges during adaptation to anomaly images. In this paper, we propose a novel \textbf{S}elf-\textbf{P}erceptinon \textbf{T}uning (\textbf{SPT}) method, aiming to enhance SAM's perception capability for anomaly segmentation. The SPT method incorporates a self-drafting tuning strategy, which generates an initial coarse draft of the anomaly mask, followed by a refinement process. Additionally, a visual-relation-aware adapter is introduced to improve the perception of discriminative relational information for mask generation. Extensive experimental results on several benchmark datasets demonstrate that our SPT method can significantly outperform baseline methods, validating its effectiveness. Models and codes will be available online.

Promptable Anomaly Segmentation with SAM Through Self-Perception Tuning

The Iterative Closest Point (ICP) algorithm suffers from sensitivity to outliers and tendency to local optima in point cloud fine registration. In this paper, we introduce a global and robust ICP framework called Granular-Ball Iterative Closest Point with MultiKernel Correntropy (GRICP). This approach transforms the point cloud into a granular ball cloud and employs MultiKernel Correntropy (MKC) as the loss function, which is designed to smooth out the effects of noise points and provide global information for registration. Specifically, we propose a coarse-grained representation of the point cloud using the granular ball model, which adaptively captures the coarse-grained features of the data and converts the point cloud into a multi-granularity ball cloud. The normal points within each granular ball help mitigate the influence of noise points. To ensure that ICP finds the globally optimal transformation, MKC is introduced to measure the distribution of registration errors, thereby offering global insights for ICP to achieve the optimal solution. The transformations based on MKC and the granular ball cloud are then derived. Extensive experiments on both simulated and real-world datasets demonstrate that GRICP delivers superior registration performance, particularly in scenarios involving large rotation offsets, partial overlaps, and Gaussian noise.  The implementation code of experiments is available at  https://anonymous.4open.science/r/GRICP-806F.

GRICP: Granular-Ball Iterative Closest Point with Multikernel Correntropy for Point Cloud Fine Registration

Training-free open-vocabulary semantic segmentation aims to explore the potential of frozen Vision-Language models for segmentation tasks. 
Recent works reform the inference process of CLIP and utilize the features from the final layer to reconstruct dense representations for segmentation, demonstrating promising performance.
However, the final layer tends to prioritize global components over local representations, leading to suboptimal robustness and effectiveness of existing methods.
In this paper, we propose CLIPSeg, a novel training-free framework that fully exploits the diverse knowledge across layers in CLIP for dense predictions.
Our study unveils two key discoveries: Firstly, the features in the middle layers exhibit high locality awareness and feature coherence compared to the final layer, based on which we propose the coherence enhanced residual attention module that generates semantic-aware attention. Secondly, despite not being directly aligned with the text, the deep layers capture valid local semantics that complement those in the final layer. Leveraging this insight, we introduce the deep semantic integration module to boost the patch semantics in the final block.
Experiments conducted on 9 segmentation benchmarks with various CLIP models demonstrate that CLIPSeg consistently outperforms all training-free methods by substantial margins, \eg, a 7.8\% improvement in average mIoU for CLIP with a ViT-L backbone, and competes with learning-based counterparts in generalizing to novel concepts in an efficient way.

Unveiling the Knowledge of CLIP for Training-Free Open-Vocabulary Semantic Segmentation

Point cloud completion aims to recover partial geometric and topological shapes caused by equipment defects or limited viewpoints. Current methods either solely rely on the 3D coordinates of the point cloud to complete it or incorporate additional images with well-calibrated intrinsic parameters to guide the geometric estimation of the missing parts. Although these methods have achieved excellent performance by directly predicting the location of complete points, the extracted features lack fine-grained information regarding the location of the missing area. To address this issue, we propose a rapid and efficient method to expand an unimodal framework into a multimodal framework. This approach incorporates a position-aware module designed to enhance the spatial information of the missing parts through a weighted map learning mechanism. In addition, we establish a Point-Text-Image triplet corpus PCI-TI and MVP-TI based on the existing unimodal point cloud completion dataset and use the pre-trained vision-language model CLIP to provide richer detail information for 3D shapes, thereby enhancing performance. Extensive quantitative and qualitative experiments demonstrate that our method outperforms state-of-the-art point cloud completion methods.

Position-Aware Guided Point Cloud Completion with CLIP Model

Knowledge base question answering (KBQA) refers to the system that produces answers to user queries by reasoning with a large-scale structured knowledge base. Advanced works have achieved great success either by generating logical forms (LFs) or directly generating answers. Although the former typically yields better performance, these generated LFs could be inaccurate, e.g., non-executable. In this regard, large language models (LLMs) have shown exciting potential for accurate generation. However, it is challenging to fine-tune an LLMs to generate LFs. This is because the context retrieved for prediction typically leads to an excessive number of reasoning paths. In this context, LLMs can generate numerous LFs corresponding to these reasoning paths, but a few LFs can result in correct answers. Thus, fine-tuning LLMs to generate answer-relevant LFs would conflict with LLMs' prior knowledge. In this work, we propose a novel learning framework, FM-KBQA, to \emph{f}ine-tune LLMs using \emph{m}ulti-task learning for \emph{KBQA}. Specifically, we propose to fine-tune LLMs using an additional objective: generating the index of reasoning paths that lead to correct answers. This will direct LLMs to pay attention to answer-relevant paths among numerous reasoning paths by completing a simple task where the selected reasoning paths can be supplementary for non-executable LFs. Directly generating answers can make LLMs pay attention to the answer-relevant reasoning paths, but it is much more challenging than generating the index of reasoning paths. To verify FM-KBQA's effectiveness, we conduct experiments on mainstream benchmarks, such as WebQuestionsSP (WQSP) and ComplexWebQuestions (CWQ). Extensive evaluations across two public benchmark datasets underscore the superiority of FM-KBQA over current state-of-the-art methods.

Promoting Knowledge Base Question Answering by Directing LLMs to Generate Task-relevant Logical Forms

The scarcity data of medical field brings the collaborative training in medical vision-language pre-training (VLP) cross different clients. Therefore, the collaborative training in medical VLP faces two challenges: First, the medical data requires privacy, thus can not directly shared across different clients. Second, medical data distribution across institutes is typically heterogeneous, hindering local model align-
ment and representation capabilities. To simultaneously overcome these two challenges, we propose the framework called personalized model selector with fused multimodal information (PMS-FM). The contribution of PMS-FM is two-fold: 1) PMS-FM uses embeddings to represent information in different formats, allowing for the fusion of multimodal data. 2) PMS-FM adapts to personalized data distributions by training multiple models. A model selector then identifies and selects the best-performing model for each individual client. Extensive experiments with multiple real-world medical datasets demonstrate the superb performance of PMS-FM over existing federated learning methods on different zero-shot classification tasks. The source code will be made available at https://github.com/addadw212/-PMS-FM

Overcoming Heterogeneous Data in Federated Medical Vision-Language Pre-training: A Triple-Embedding Model Selector Approach

Video Temporal Grounding (VTG) strives to accurately pinpoint event timestamps in a specific video using linguistic queries, significantly impacting downstream tasks like video browsing and editing. Unlike traditional task-specific models, Video Large Language Models (video LLMs) can handle multiple tasks concurrently in a zero-shot manner. Consequently, exploring the application of video LLMs for VTG tasks has become a burgeoning research area.
However, despite considerable advancements in video content understanding, video LLMs often struggle to accurately pinpoint timestamps within videos, limiting their effectiveness in VTG tasks. To address this, we introduce VTG-LLM, a model designed to enhance video LLMs' timestamp localization abilities. Our approach includes: (1) effectively integrating timestamp knowledge into visual tokens; (2) incorporating absolute-time tokens to manage timestamp knowledge without concept shifts; and (3) introducing a lightweight, high-performance, slot-based token compression technique designed to accommodate the demands of a large number of frames to be sampled for VTG tasks.
Additionally, we present VTG-IT-120K, a collection of publicly available VTG datasets that we have re-annotated to improve upon low-quality annotations.
Our comprehensive experiments demonstrate the superior performance of VTG-LLM in comparison to other video LLM methods across a variety of VTG tasks.

VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding

Knowledge distillation (KD) has recently gained great success in the field of object detection. By transferring the knowledge of spatial
or channel domain form the teacher model to the student model, it allows for more compact representation with minimal performance loss. Despite this progress, existing KD methods typically treat the knowledge from spatial or channel domains independently, ignoring the exploitation of the mutual relationship between these domains. In this work, we first explore the connection between spatial and channel domains, and find there exists a strong correlation between them, i.e., the salient channels tend to contain significant object regions in the spatial domain. Motivated by this observation, we propose DCSF-KD, a novel Dynamic Channel-wise Spatial Feature Knowledge Distillation, a novel Dual-Domain knowledge distillation framework for object detection by fully exploiting both spatial and channel knowledge. Specifically, We introduce channel-wise spatial feature distillation and global channel attention distillation, leveraging information from both domains to boost the accuracy of the student network. Experiments demonstrates that our DDKD outperforms existing detection methods on both homogeneous and heterogeneous teacher-student network pairs. For example, when using the MaskRCNN-Swin detector as the teacher, and basing on RetinaNet and FCOS with ResNet-50 on COCO2017, our DDKD can achieve 41.9% and 44.1% 𝑚𝐴𝑃, respectively. Code would be available after review.

Downloads

Next from AAAI 2025

Multi-View Collaborative Learning Network for Speech Deepfake Detection

Similar lecture

Hand-Model-Aware Sign Language Recognition

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2025

Multi-View Collaborative Learning Network for Speech Deepfake Detection

Similar lecture

Hand-Model-Aware Sign Language Recognition

Downloads