United States

Video procedure planning, i.e., planning a sequence of action steps given the video frames of start and goal states, is an essential ability for embodied AI. Recent works utilize Large Language Models (LLMs) to generate enriched action step description texts to guide action step decoding. Although introducing LLMs, these methods decode the action steps into a close set of one-hot vectors, limiting the model&#39;s capability of generalizing to new steps or tasks. Additionally, the fixed action step descriptions based on world-level commonsense may contain noise in specific samples of visual states. In this paper, we propose PlanLLM, a cross-modal joint learning framework with LLMs for video procedure planning. We propose LLM-Enhanced Planning module which fully use the generalization ability of LLMs to produce free form planning outputs and to enhance action step decoding. We also propose Mutual Information Maximization module to connect world-level commonsense of step descriptions and sample-specific information of visual states, enabling LLMs to employ the reasoning ability to generate step sequence. With the assistance of LLMs, our method can deal with both close set and open vocabulary procedure planning tasks. Our PlanLLM achieves state-of-the-art performance on three benchmarks, demonstrating the effectiveness of our designs.

AAAI 2025

PlanLLM: Video Procedure Planning with Refinable Large Language Models

Video procedure planning, i.e., planning a sequence of action steps given the video frames of start and goal states, is an essential ability for embodied AI. Recent works utilize Large Language Models (LLMs) to generate enriched action step description texts to guide action step decoding. Although introducing LLMs, these methods decode the action steps into a close set of one-hot vectors, limiting the model's capability of generalizing to new steps or tasks. Additionally, the fixed action step descriptions based on world-level commonsense may contain noise in specific samples of visual states. In this paper, we propose PlanLLM, a cross-modal joint learning framework with LLMs for video procedure planning. We propose LLM-Enhanced Planning module which fully use the generalization ability of LLMs to produce free form planning outputs and to enhance action step decoding. We also propose Mutual Information Maximization module to connect world-level commonsense of step descriptions and sample-specific information of visual states, enabling LLMs to employ the reasoning ability to generate step sequence. With the assistance of LLMs, our method can deal with both close set and open vocabulary procedure planning tasks. Our PlanLLM achieves state-of-the-art performance on three benchmarks, demonstrating the effectiveness of our designs.

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.



The goal of video moment retrieval and highlight detection is to identify specific segments and highlights based on a given text query. With the rapid growth of video content and the overlap between these tasks, recent works have addressed both simultaneously. However, they still struggle to fully capture the overall video context, making it challenging to determine which words are most relevant. In this paper, we present a novel Video Context-aware Keyword Attention module that overcomes this limitation by capturing keyword variation within the context of the entire video. To achieve this, we introduce a video context clustering module that provides concise representations of the overall video context, thereby enhancing the understanding of keyword dynamics. Furthermore, we propose a keyword weight detection module with keyword-aware contrastive learning that incorporates keyword information to enhance fine-grained alignment between visual and textual features. Extensive experiments on the QVHighlights, TVSum, and Charades-STA benchmarks demonstrate that our proposed method significantly improves performance in moment retrieval and highlight detection tasks compared to existing approaches.

Watch Video, Catch Keyword: Context-aware Keyword Attention for Moment Retrieval and Highlight Detection

Molecular representation learning plays a crucial role in various downstream tasks, such as molecular property prediction and drug design. To accurately represent molecules, Graph Neural Networks (GNNs) and Graph Transformers (GTs) have shown potential in the realm of self-supervised pre-training. However, existing approaches often overlook the relationship between molecular structure and electronic information, as well as the internal semantic reasoning within molecules. This omission of fundamental chemical knowledge in graph semantics leads to incomplete molecular representations, missing the integration of structural and electronic data. To address these issues, we introduce MOL-Mamba, a framework that enhances molecular representation by combining structural and electronic insights. MOL-Mamba consists of an **Atom \& Fragment Mamba-Graph (MG)** for hierarchical structural reasoning and a **Mamba-Transformer (MT) fuser** for integrating molecular structure and electronic correlation learning. Additionally, we propose a **Structural Distribution Collaborative Training** and **E-semantic Fusion Training** framework to further enhance molecular representation learning. Extensive experiments demonstrate that MOL-Mamba outperforms state-of-the-art baselines across eight molecular datasets. Visualization experiments also provide insights into what MOL-Mamba has learned. We will release the code after the anonymous review process.

MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insights

The success of visual tracking has been largely driven by datasets with manual box annotations. However, these box annotations require tremendous human effort, limiting the scale and diversity of existing tracking datasets. In this work, we present a novel Self-Supervised Tracking framework, named \textbf{SSTrack}, designed to eliminate the need of box annotations. Specifically, a decoupled spatio-temporal consistency training framework is proposed to learn rich target information across timestamps through global spatial localization and local temporal association. This allows for the simulation of appearance and motion variations of instances in real-world scenarios. Furthermore, an instance contrastive loss is designed to learn instance-level correspondences from a multi-view perspective, offering robust instance supervision without additional labels. This new design paradigm enables SSTrack to effectively learn generic tracking representations in a self-supervised manner, while reducing reliance on extensive box annotations. Extensive experiments on nine benchmark datasets demonstrate that SSTrack surpasses \textit{SOTA} self-supervised tracking methods, achieving an improvement of more than 25.3\%, 20.4\%, and 14.8\% in AUC (AO) score on the GOT10K, LaSOT, TrackingNet datasets, respectively. Consequently, SSTrack significantly reduces the performance gap between self- and fully-supervised trackers.

Decoupled Spatio-Temporal Consistency Learning for Self-Supervised Tracking

Prior efforts in light-weight model development mainly centered on CNN and Transformer-based designs yet faced persistent challenges. CNNs adept at local feature extraction compromise resolution while Transformers offer global reach but escalate computational demands $\mathcal{O}(N^2)$. This ongoing trade-off between accuracy and efficiency remains a significant hurdle. Recently, state space models (SSMs), such as Mamba, have shown outstanding performance and competitiveness in various tasks such as language modeling and computer vision, while reducing the time complexity of global information extraction to $\mathcal{O}(N)$. Inspired by this, this work proposes to explore the potential of visual state space models in light-weight model design and introduce a novel efficient model variant dubbed EfficientVMamba. Concretely, our EfficientVMamba integrates a atrous-based selective scan approach by efficient skip sampling, constituting building blocks designed to harness both global and local representational features. Additionally, we investigate the integration between SSM blocks and convolutions, and introduce an efficient visual state space block combined with an additional convolution branch, which further elevate the model performance. Experimental results show that, EfficientVMamba scales down the computational complexity while yields competitive results across a variety of vision tasks. For example, our EfficientVMamba-S with $1.3$G FLOPs improves Vim-Ti with $1.5$G FLOPs by a large margin of $5.6\%$ accuracy on ImageNet.

EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba

As the academic landscape expands, the challenge of efficiently identifying potentially high-impact articles among the vast number of newly published works becomes critical. This paper introduces a promising approach, leveraging the capabilities of fine-tuned LLMs to predict the future impact of newborn articles solely based on titles and abstracts. Moving beyond traditional methods heavily reliant on external information, the proposed method discerns the shared semantic features of highly impactful papers from a large collection of title-abstract and potential impact pairs. These semantic features are further utilized to regress an improved metric, $TNCSI_{SP}$, which has been endowed with value, field, and time normalization properties. Additionally, a comprehensive dataset has been constructed and released for fine-tuning the LLM, containing over 12,000 entries with corresponding titles, abstracts, and $TNCSI_{SP}$. The quantitative results, with an NDCG@20 of 0.901, demonstrate that the proposed approach achieves state-of-the-art performance in predicting the impact of newborn articles when compared to competitive counterparts. Finally, we demonstrate a real-world application for predicting the impact of newborn journal articles to demonstrate its noteworthy practical value. Overall, our findings challenge existing paradigms and propose a shift towards a more content-focused prediction of academic impact, offering new insights for assessing newborn article impact.

From Words to Worth: Newborn Article Impact Prediction with LLM

In the field of class-agnostic counting (CAC), counting only objects of interest that are similar to exemplars in multi-class scenarios has been a challenging task. To address this challenge, recent research has proposed the extract-and-match paradigm based on the vision transformer (ViT) architecture. However, although this paradigm can improve the accuracy of exemplar-similar object identification, it overly emphasizes the role of the ViT structure. To address this shortcoming, this work introduces a more generalized prompt-before-extract paradigm on top of the extract-and-match paradigm and designs a pure convolutional neural network (CNN) model named PBECount. In addition, an innovative loss function, a post-processing strategy, and a dynamic threshold method are proposed to enhance the detection performance of the proposed model when the probability maps are used as ground truth during model training. The experimental results on the FSC-147 and CARPK datasets demonstrate that the proposed PBECount can identify whether unknown class objects are similar to exemplars and outperform the state-of-the-art CAC methods in terms of accuracy and generalization.

PBECount: Prompt-Before-Extract Paradigm for Class-Agnostic Counting

Adversarial attack and defense have been extensively explored in classification tasks, but their study in semantic segmentation remains limited. Moreover, current attacks fail to act as strong underlying attacks for adversarial training (AT), making it difficult to achieve segmentation robustness against strong attacks. In this paper, we present RP-PGD, a novel Region-and-Prototype based Projected Gradient Descent attack tailored to fool segmentation models. In particular, we propose a region-based attack, which leverages a spatial-temporal way to separate the pixels into three disjoint regions, and highlights the attack on the crucial True Region and Boundary Region. Moreover, we introduce a prototype-based attack to disrupt the feature space, further enhancing the attack capability. To boost the robustness of segmentation models, we inject adversaries generated by RP-PGD into the clean data and perform AT. Extensive experiments on multiple datasets showcase that RP-PGD generates adversaries with faster convergence and stronger attack effectiveness, surpassing state-of-the-art attacks by a large margin. Consequently, RP-PGD serves as a strong underlying attack for segmentation models to perform AT, assisting them in defending against a variety of strong attacks without incurring additional computational costs during inference.

RP-PGD: Boosting Segmentation Robustness with a Region-and-Prototype Based Adversarial Attack

Data augmentation is expected to bring about unseen features
of training set, enhancing the model’s ability to generalize
in situations where data is limited. Generative image models trained on large web-crawled datasets such as LAION
are known to produce images with stereotypes and imperceptible bias when used to augment training data, owing to
dataset misalignment and the generator’s ignorance of the
downstream model. We improve downstream task awareness
in generated images by proposing a task-aware fine-tuning
strategy that actively detects failures of downstream task in
the target model to fine-tune the generation process between
epochs. The dynamic fine-tuning strategy is achieved by (1)
inspecting misalignment between generated data and original
data via VLM captioners and (2) adjusts both prompts and
diffusion model so that the strategy dynamically guides the
generator by focusing on the detected bias of VLM. This is
done via re-captioning the overfitted data as well as finetuning the diffusion trajectory in a contrastive manner. To cooperate with the VLM captioner, the contrastive fine-tuning
process dynamically adjusts different parts of the diffusion
trajectory based on detected misalignment, thus shifting the
the generated distribution away from making the downstream
model overfit. Our experiments on few-shot class incremental
learning show that our instruction-guided finetuning strategy
consistently assists the downstream model with higher classification accuracy compared to generative data augmentation
baselines such as Stable Diffusion and GPT-4o, and state-of-the-art non-generative strategies.

Instruct Where the Model Stucks: Generative Data Augmentation via Guided Self-contrastive Fine-tuning

Video question answering (VideoQA) aims to answer natural language questions according to the given videos. Although existing models perform well in the factoid VideoQA task, they still face challenges in deep video understanding (DVU) task, which focuses on story videos. Compared to factoid videos, the most significant feature of story videos is storylines, which are composed of complex interactions and long-range evolvement of core story topics including characters, actions and locations. Understanding these topics requires models to possess DVU capability. However, existing DVU datasets rarely organize questions according to these story topics, making them difficult to comprehensively assess VideoQA models' DVU capability of complex storylines. Additionally, the question quantity and video length of these dataset are limited by high labor costs of handcrafted dataset building method. In this paper, we devise a large language model based multi-agent collaboration framework, StoryMind, to automatically generate a new large-scale DVU dataset. The dataset, FriendsQA, derived from the renowned sitcom $\textit{Friends}$ with an average episode length of 1,358 seconds, contains 44.6K questions evenly distributed across 14 fine-grained topics. Finally, We conduct comprehensive experiments on 10 state-of-the-art VideoQA models using the FriendsQA dataset and discuss future research directions of DVU for story videos based on the results accordingly.

FriendsQA: A New Large-Scale Deep Video Understanding Dataset with Fine-grained Topic Categorization for Story Videos

Point Transformers (PoinTr) have shown great potential in point cloud completion recently. Nevertheless, effective domain adaptation that improves transferability toward target domains remains unexplored. In this paper, we delve into this topic and empirically discover that direct feature alignment on point Transformer’s CNN backbone only brings limited improvements since it cannot guarantee sequence-wise domain-invariant features in the Transformer. To this end, we propose a pioneering Domain Adaptive Point Transformer (DAPoinTr) framework for point cloud completion. DAPoinTr consists of three novel components: Domain Query-based Feature Alignment (DQFA), Point Token-wise Feature alignment (PTFA), and Voted Prediction Consistency (VPC). In particular, DQFA is presented to narrow the global domain gaps from the sequence via the presented domain proxy and domain query at the Transformer encoder and decoder, respectively. PTFA is proposed to close the local domain shifts by aligning the tokens, i.e., point proxy and dynamic query, at the Transformer encoder and decoder, respectively. VPC is designed to consider different Transformer decoders as multiple of experts (MoE) for ensembled prediction voting and pseudo-label generation. Extensive experiments with visualization on several challenging domain adaptation benchmarks demonstrate the effectiveness and superiority of our DAPoinTr compared with other state-of-the-art methods.

PlanLLM: Video Procedure Planning with Refinable Large Language Models

Downloads

Next from AAAI 2025

Watch Video, Catch Keyword: Context-aware Keyword Attention for Moment Retrieval and Highlight Detection

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES