United States

In the domain of multivariate time series analysis, the concept of channel independence has been increasingly adopted, demonstrating excellent performance due to its ability to eliminate noise and the influence of irrelevant variables. However, such a concept often simplifies the complex interactions among channels, potentially leading to information loss. To address this challenge, we propose a strategy of channel independence followed by mixing. Based on this strategy, we introduce CSformer, a novel framework featuring a two-stage multiheaded self-attention mechanism. This mechanism is designed to extract and integrate both channel-specific and sequence-specific information. Distinctively, CSformer employs parameter sharing to enhance the cooperative effects between these two types of information. Moreover, our framework effectively incorporates sequence and channel adapters, significantly improving the model&#39;s ability to identify important information across various dimensions. Extensive experiments on several real-world datasets demonstrate that CSformer achieves state-of-the-art results in terms of overall performance.

AAAI 2025

CSformer: Combining Channel Independence and Mixing for Robust Multivariate Time Series Forecasting

In the domain of multivariate time series analysis, the concept of channel independence has been increasingly adopted, demonstrating excellent performance due to its ability to eliminate noise and the influence of irrelevant variables. However, such a concept often simplifies the complex interactions among channels, potentially leading to information loss. To address this challenge, we propose a strategy of channel independence followed by mixing. Based on this strategy, we introduce CSformer, a novel framework featuring a two-stage multiheaded self-attention mechanism. This mechanism is designed to extract and integrate both channel-specific and sequence-specific information. Distinctively, CSformer employs parameter sharing to enhance the cooperative effects between these two types of information. Moreover, our framework effectively incorporates sequence and channel adapters, significantly improving the model's ability to identify important information across various dimensions. Extensive experiments on several real-world datasets demonstrate that CSformer achieves state-of-the-art results in terms of overall performance.

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.



Current research on adversarial attacks mainly focuses on RGB trackers, with no existing methods for attacking RGB-T cross-modal trackers. To fill this gap and overcome its challenges, we propose a coarse-to-fine cross-modal adversarial patch generation framework, achieving cross-modal stealth. On the one hand, we design a coarse-to-fine architecture grounded in the latent space to progressively and precisely uncover the vulnerabilities of RGB-T trackers. On the other hand, we introduce a correlation-breaking loss that disrupts the modal coupling within the tracker, spanning from the pixel to the semantic level. These two design elements ensure that the proposed method can overcome the obstacles posed by cross-modal information complementarity in implementing attacks. Furthermore, to enhance the reliable application of the proposed adversarial patches in the real world, we develop a point-tracking-based reprojection strategy that effectively mitigates performance degradation caused by multi-angle distortion during imaging. Extensive comparative and generalization experiments demonstrate the superiority of our attack method.

Cross-Modal Stealth: A Coarse-to-Fine Attack Framework for RGB-T Tracker

Existing Salient Object Ranking (SOR) aims to infer ranking of salient objects based on their saliency degree. However, it tends to only focus on salient objects while neglecting non-salient ones. This coarse-grained ranking limits the performance of downstream tasks. For instance, in image retrieval tasks, focusing solely on the relationship between salient objects is insufficient for achieving fine-grained scene analysis, which may result in retrieved results that do not satisfy user requirements. High-quality retrieval requires fine-grained analysis, making it essential to rank non-salient objects. Based on this need, we propose a new task: Fine-grained Object Importance Ranking in 360$^{\rm o}$ Scenes (FOIR-360), which focus on predicting the relative importance of "ALL objects'' at the instance-level. Our task takes into account all objects, allowing us to refine the original "coarse-grained'' to a "fine-grained'' level. Currently, the main challenge for this new task is the lack of supervised data for model training or even for model testing. Therefore, we propose a novel weakly supervised method to address the shortage of datasets. Furthermore, to the best of our knowledge, there is no existing suitable annotation protocol for this new task. The main reason is that annotating fine-grained rankings is extremely difficult, especially in panoramic scenes that contain numerous instances where even humans are unable to determine which one is more important than others. As the first attempt, we introduce a new annotation protocol designed to highlight the ranking of objects that are non-salient yet still important. Based on this protocol, we construct the first fine-grained 360Rank dataset. In summary, all these new task, weakly supervised method, annotation protocol, and dataset have the potential to drive advancements in the field. Both the code and dataset are publicly available at [https://github.com/noname965/FOIR-360](https://github.com/noname965/FOIR-360).

Fine-Grained Perception in Panoramic Scenes: A Novel Task, Dataset, and Method for Object Importance Ranking

Multi-shape matching is a central problem in various applications of computer vision and graphics, where cycle consistency constraints play a pivotal role. For this issue, we propose a novel and efficient approach that models multi-shapes as directed graphs for two-stage optimization, i.e., optimizing pairwise correspondence accuracy using landmarks, and refining matching consistency through cycle consistency basis. Specifically, we utilize local mapping distortion to identify landmarks and extract the dimension of the functional space, which is then used to upsample in the spectral domain, thereby producing smoother results. Next, to optimize the consistency of correspondences, we introduce the cycle consistency basis, which succinctly describes all consistent cycles in the collection. We then propose cycle consistency refinement, which resolves inconsistencies in cycles efficiently via the alternating direction method of multipliers. Our approach simultaneously balances the accuracy and consistency of multi-shape matching, achieving lower correspondence errors. Extensive experiments on several public datasets demonstrate the superiority of our approach over current state-of-the-art methods.

Multi-Shape Matching with Cycle Consistency Basis via Functional Maps

Image feature matching is a cardinal problem in computer vision, aiming to establish accurate correspondences between two-view images. Existing methods are constrained by the performance of feature extractors and struggle to capture local information affected by sparse texture or occlusions. Recognizing that human eyes consider not only similar local geometric features but also high-level semantic information of scene objects when matching images, this paper introduces SemaGlue. This novel algorithm perceives and incorporates semantic information into the matching process. In contrast to recent approaches that leverage semantic consistency to narrow the scope of matching areas, SemaGlue achieves semantic amalgamation with the designed Semantic-Aware Fusion (SAF) Block by injecting abundant semantic features from the pre-trained segmentation model. Moreover, the Cross-Domain Alignment (CDA) Block is proposed to address domain alignment issues, bridging the gaps between semantic and geometric domains to ensure applicable semantic amalgamation. Extensive experiments demonstrate that SemaGlue outperforms state-of-the-art methods across various applications such as homography estimation, relative pose estimation, and visual localization.

Matching While Perceiving: Enhance Image Feature Matching with Applicable Semantic Amalgamation

In real-world scenarios, acquiring dense depth measurements is challenging, so typically sparse depth data is obtained. This has led to studies in depth completion to complete depth maps. Existing methods have primarily focused on in-domain generalization, which targets performance on specific datasets, while domain-generalizable depth completion remains a challenge due to domain shifts. In this paper, we leverage the depth prior provided by a pre-trained depth diffusion model, which implicitly understands how to fill in depth information. By utilizing the comprehensive prior knowledge across various scenes, we enhance the generalizability and quality of depth maps in depth completion. We present the prior-based depth completion pipeline that effectively integrates sparse measurements with relative depth prior, enabling zero-shot metric depth completion. To achieve desirable solutions, we perform an adaptation during the reverse sampling process using the optimization loop as hard guidance. Additionally, we propose the outlier filtering method based on a prior about the depth affinity relationships. We also propose the outlier filtering method based on a prior about the depth affinity relationships. Our zero-shot adaptation method demonstrates generalization across various domain datasets, achieving an average performance improvement of 22.8% over previous state-of-the-art methods, and improves spatial understanding by sharpening details.

Zero-shot Depth Completion via Test-time Alignment with Affine-invariant Depth Prior

In search scenarios, user experience can be hindered by erroneous queries due to typos, voice errors, or knowledge gaps. Therefore, query correction is crucial for search engines. Current correction models, usually small models trained on specific data, often struggle with queries beyond their training scope or those requiring contextual understanding. While the advent of Large Language Models (LLMs) offers a potential solution, they are still limited by their pre-training data and inference cost, particularly for complex queries, making them not always effective for query correction. To tackle these, we propose $\mathrm{Trigger}^3$, a framework that integrates the traditional correction model and LLM for query correction, capable of adaptively choosing the appropriate correction method based on the query and the correction results from the traditional correction model and LLM. $\mathrm{Trigger}^3$ first employs a correction trigger to filter out correct queries. Incorrect queries are then corrected by the traditional correction model. If this fails, an LLM trigger is activated to call the LLM for correction. Finally, for queries that no model can correct, a fallback trigger decides to return the original query. Extensive experiments demonstrate $\mathrm{Trigger}^3$ outperforms correction baselines while maintaining efficiency.

Trigger$^3$: Refining Query Correction via Adaptive Model Selector

Recent large-scale pre-trained diffusion models have demonstrated a powerful generative ability to produce high-quality videos from detailed text descriptions. However, exerting control over the motion of objects in videos generated by any video diffusion model remains
a challenging problem. In this paper, we propose a novel zero-shot moving object trajectory control framework, Motion-Zero, to enable arbitrary single-object-trajectory control for the text-to-video diffusion model.  To this end, an initial noise prior module is designed to provide a position-based prior to improve the stability of the appearance of the moving object and the accuracy of position. In addition, based on the attention map of the U-Net, spatial constraints are directly applied to the denoising process of diffusion models, which further ensures the positional consistency of moving objects during the inference. Furthermore, temporal consistency is guaranteed with a proposed shift temporal attention mechanism. Our method can be flexibly applied to various state-of-the-art video diffusion models without any training process. Extensive experiments demonstrate our proposed method can control the motion trajectories of arbitrary objects while preserving the original ability to generate high-quality videos.

Motion-Zero: A Zero-Shot Trajectory Control Framework of Moving Object for Diffusion-Based Video Generation

View transformation robustness (VTR) is critical for deep-learning-based multi-view 3D object reconstruction models, which indicates the methods' stability under inputs with various view transformations. However, existing research seldom focused on view transformation robustness in multi-view 3D object reconstruction. One direct way to improve the models' VTR is to produce data with more view transformations and add them to model training.  Recent progress on large vision models, particularly Stable Diffusion models, has provided great potential for generating 3D models or synthesizing novel view images with only a single image input. Directly deploying these models at inference consumes heavy computation resources and their robustness to view transformations is not guaranteed either. To fully utilize the power of Stable Diffusion models without extra inference computation burdens, we propose to generate novel views with Stable Diffusion models for better view transformation robustness. Instead of synthesizing random views, we propose a reconstruction error-guided view selection method, which considers the reconstruction errors' spatial distribution of the 3D predictions and chooses the views that could cover the reconstruction errors as much as possible. The methods are trained and tested on sets with large view transformations to validate the 3D reconstruction models' robustness to view transformations. Extensive experiments demonstrate that the proposed method can outperform state-of-the-art 3D reconstruction methods and other view transformation robustness comparison methods.

View Transformation Robustness for Multi-View 3D Object Reconstruction with Reconstruction Error-Guided View Selection

Dynamic quantization has attracted rising attention in image super-resolution (SR) as it expands the potential of heavy SR models onto mobile devices while preserving competitive performance. Most current methods explore layer-to-bit configuration upon varying local regions, adaptively allocating the bit to each layer and patch. Despite the benefits, they still fall short in the tradeoff of SR accuracy and quantization efficiency. Apart from this, adapting the quantization level for each layer individually can disturb the original inter-layer relationships, thus diminishing the representation capability of quantized models. In this work, we propose Granular-DQ, which takes advantage of multi-granularity clues and local patch statistics, achieving a distinctive patch-wise and layer-invariant dynamic quantization paradigm. Specifically, Granular-DQ initiates by developing a granularity-bit controller to apprehend the coarse-to-fine granular representations of local patches, matching their proportional contribution to the entire image to determine the proper bit-width allocation. On this premise, we investigate the interrelationships between bit-width and information density within high-bit patches, establishing a soft gate that enables further fine-grained dynamic bit adaption. Extensive experiments validate the superiority of Granular-DQ in the trade-off between efficiency and accuracy over recent state-of-the-art methods on various SR models. Code is available in our supplementary material.

Thinking in Granularity: Dynamic Quantization for Image Super-Resolution by Intriguing Multi-Granularity Clues

Recently, large language models (LLMs) and multimodal large language models (MLLMs) have demonstrated promising results on document visual question answering (VQA) task, particularly after training on document instruction datasets. An effective evaluation method for document instruction data is crucial in constructing instruction data with high efficacy, which, in turn, facilitates the training of LLMs and MLLMs for document VQA. However, most existing evaluation methods for instruction data are limited to the textual content of the instructions themselves, thereby hindering the effective assessment of document instruction datasets and constraining their construction. In this paper, we propose ProcTag, a data-oriented method that assesses the efficacy of document instruction data. ProcTag innovatively performs tagging on the execution process of instructions rather than the instruction text itself. By leveraging the diversity and complexity of these tags to assess the efficacy of the given dataset, ProcTag enables selective sampling or filtering of document instructions. Furthermore, DocLayPrompt, a novel semi-structured layout-aware document prompting strategy, is proposed for effectively representing documents. Experiments demonstrate that sampling existing open-sourced and generated document VQA/instruction datasets with ProcTag significantly outperforms current methods for evaluating instruction data. Impressively, with ProcTag-based sampling in the generated document datasets, only 30.5\% of the document instructions are required to achieve 100\% efficacy compared to the complete dataset.

Premium content

Next from AAAI 2025

Cross-Modal Stealth: A Coarse-to-Fine Attack Framework for RGB-T Tracker

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES