United States

Video Grounding (VG) aims to locate the desired segment from a video given a sentence query. Recent studies have found that current VG models are prone to over-rely the groundtruth moment annotation distribution biases in the training set. To discourage the standard VG model&#39;s behavior of exploiting such temporal annotation biases and improve the model generalization ability, we propose multiple negative augmentations in a hierarchical way, including cross-video augmentations from clip-/video-level, and self-shuffled augmentations with masks. These augmentations can effectively diversify the data distribution so that the model can make more reasonable predictions instead of merely fitting the temporal biases. However, directly adopting such data augmentation strategy may inevitably carry some noise shown in our cases, since not all of the handcrafted augmentations are semantically irrelevant to the groundtruth video. To further denoise and improve the grounding accuracy, we design a multi-stage curriculum strategy to adaptively train the standard VG model from easy to hard negative augmentations. Experiments on newly collected Charades-CD and ActivityNet-CD datasets demonstrate our proposed strategy can improve the performance of the base model on both i.i.d and o.o.d scenarios.

AAAI 2023

Curriculum Multi-Negative Augmentation for Debiased Video Grounding

fairness & privacy

image and video retrieval

video understanding & activity analysis

multi-modal vision

language and vision

bias

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-23 is the Thirty-Seventh AAAI Conference on Artificial Intelligence. The theme of this conference is to create collaborative bridges within and beyond AI. Like previous AAAI conferences, AAAI-23 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and two new activities: a Bridge Program and a Lab Program. Many of these activities are tailored to the theme of bridges and all are selected according to the highest standards, with additional programs for students and young researchers. 
AAAI is providing you with a conference planner, which you can use to help organize your itinerary of activities. This includes talks to attend in person, talks to attend remotely, breaks with colleagues and your site seeing activities. To access this conference planner, please go to [https://aaai-2023.takemobi.io](https://aaai-2023.takemobi.io).

In order to access this site, you need to register. If you haven't already, please register [here](https://aaai.org/Conferences/AAAI-23/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.

Video Grounding (VG) aims to locate the desired segment from a video given a sentence query. Recent studies have found that current VG models are prone to over-rely the groundtruth moment annotation distribution biases in the training set. To discourage the standard VG model's behavior of exploiting such temporal annotation biases and improve the model generalization ability, we propose multiple negative augmentations in a hierarchical way, including cross-video augmentations from clip-/video-level, and self-shuffled augmentations with masks. These augmentations can effectively diversify the data distribution so that the model can make more reasonable predictions instead of merely fitting the temporal biases. However, directly adopting such data augmentation strategy may inevitably carry some noise shown in our cases, since not all of the handcrafted augmentations are semantically irrelevant to the groundtruth video. To further denoise and improve the grounding accuracy, we design a multi-stage curriculum strategy to adaptively train the standard VG model from easy to hard negative augmentations. Experiments on newly collected Charades-CD and ActivityNet-CD datasets demonstrate our proposed strategy can improve the performance of the base model on both i.i.d and o.o.d scenarios.

poster

The generation of bimanual object manipulation sequences given a semantic action label has broad applications in collaborative robots or augmented reality. This relatively new problem differs from existing works that generate whole-body motions without any object interaction as it now requires the model to additionally learn the spatio-temporal relationship that exists between the human joints and object motion given said label. To tackle this task, we leverage the varying degree each muscle or joint is involved during object manipulation. For instance, the wrists act as the prime movers for the objects while the finger joints are angled to provide a firm grip. The remaining body joints are the least involved in that they are positioned as naturally and comfortably as possible. We thus design an architecture that comprises 3 main components: (i) a graph recurrent network that generates the wrist and object motion, (ii) an attention-based recurrent network that estimates the required finger joint angles given the graph configuration, and (iii) a recurrent network that reconstructs the body pose given the locations of the wrist. We evaluate our approach on the KIT Motion Capture and KIT RGBD Bimanual Manipulation datasets and show improvements over a simplified approach that treats the entire body as a single entity, and existing whole-body-only methods.

Action-Conditioned Generation of Bimanual Object Manipulation Sequences

Monocular depth estimation is a challenging problem on which deep neural networks have demonstrated great potential. However, depth maps predicted by existing deep models usually lack fine-grained details due to the convolution operations and the down-samplings in networks. We find that increasing input resolution is helpful to preserve more local details while the estimation at low resolution is more accurate globally. Therefore, we propose a novel depth map fusion module to combine the advantages of estimations with multi-resolution inputs. Instead of merging the low- and high-resolution estimations equally, we adopt the core idea of Poisson fusion, trying to implant the gradient domain of high-resolution depth into the low-resolution depth. While classic Poisson fusion requires a fusion mask as supervision, we propose a self-supervised framework based on guided image filtering. We demonstrate that this gradient-based composition performs much better at noisy immunity, compared with the state-of-the-art depth map fusion method. Our lightweight depth fusion is one-shot and runs in real-time, making our method 80X faster than a state-of-the-art depth fusion method. Quantitative evaluations demonstrate that the proposed method can be integrated into many fully convolutional monocular depth estimation backbones with a significant performance boost, leading to state-of-the-art results of detail enhancement on depth maps. 

Multi-resolution Monocular Depth Map Fusion by Self-supervised Gradient-based Composition

Generalizing models trained on normal visual conditions to target domains under adverse conditions is demanding in the practical systems. One prevalent solution is to bridge the domain gap between clear- and adverse-condition images to make satisfactory prediction on the target. However, previous methods often reckon on additional reference images of the same scenes taken from normal conditions, which are quite tough to collect in reality. Furthermore, most of them mainly focus on individual adverse condition such as nighttime or foggy, weakening the model versatility when encountering other adverse weathers. To overcome the above limitations, we propose a novel framework, Visibility Boosting and Logit-Constraint learning (VBLC), tailored for superior normal-toadverse adaptation. VBLC explores the potential of getting rid of reference images and resolving the mixture of adverse conditions simultaneously. In detail, we first propose the visibility boost module to dynamically improve target images via certain priors in the image level. Then, we figure out the overconfident drawback in the conventional cross-entropy loss for self-training method and devise the logit-constraint learning, which enforces a constraint on logit outputs during training to mitigate this pain point. To the best of our knowledge, this is a new perspective for tackling such a challenging task. Extensive experiments on two normal-to-adverse domain adaptation benchmarks, i.e., Cityscapes to ACDC and Cityscapes to FoggyCityscapes + RainCityscapes, verify the effectiveness of VBLC, where it establishes the new state of the art.

VBLC: Visibility Boosting and Logit-Constraint Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions

Low-resource relation extraction (LRE) aims to extract relations from limited labeled corpora.  Existing work takes advantages of self-training or distant supervision to expand the limited labeled data in the data-driven approaches, while the selection bias of pseudo labels may cause the error accumulation in subsequent relation classification. To address this issue, this paper proposes fmLRE, an iterative feedback method based on feature mapping similarity calculation to improve the accuracy of pseudo labels. First, it calculates the similarities between pseudo-label and real-label data of the same category in a feature mapping space based on semantic features of labeled dataset after feature projection. Then, it fine-tunes initial model according to the iterative process of reinforcement learning. Finally, the similarity is used as a threshold for screening high-precision pseudo-labels and the basis for setting different rewards, which also acts as a penalty term for the loss function of relation classifier. Experimental results demonstrate that fmLRE achieves the state-of-the-art performance compared with strong baselines on two public datasets.

fmLRE: A Low-resource Relation Extraction Model based on Feature Mapping Similarity Calculation

Pareto Front Learning (PFL) was recently introduced as an effective approach to obtain a mapping function from a given trade-off vector to a solution on the Pareto front, which solves the multi-objective optimization (MOO) problem. Due to the inherent trade-off between conflicting objectives, PFL offers a flexible approach in many scenarios in which the decision makers can not specify the preference of one Pareto solution over another, and must switch between them depending on the situation. However, existing PFL methods ignore the relationship between the solutions during the optimization process, which hinders the quality of the obtained front. To overcome this issue, we propose a novel PFL framework namely PHN-HVI, which employs a hypernetwork to generate multiple solutions from a set of diverse trade-off preferences and enhance the quality of the Pareto front by maximizing the Hypervolume indicator defined by these solutions. The experimental results on several MOO machine learning tasks show that the proposed framework significantly outperforms the baselines in producing the trade-off Pareto front.

Improving Pareto Front Learning via Multi-Sample Hypernetworks

We investigate the sample complexity of learning the optimal arm for multi-task bandit problems. Arms consist of two components: one that is shared across tasks (that we call representation) and one that is task-specific (that we call predictor). The objective is to learn the optimal (representation, predictor)-pair for each task, under the assumption that the optimal representation is common to all tasks. Within this framework, efficient learning algorithms should transfer knowledge across tasks. We consider the best-arm identification problem for a fixed confidence, where, in each round, the learner actively selects both a task, and an arm, and observes the corresponding reward. We derive instance-specific sample complexity lower bounds satisfied by any $(\delta_G,\delta_H)$-PAC algorithm (such an algorithm identifies the best representation with probability at least $1-\delta_G$, and the best predictor for a task with probability at least $1-\delta_H$). We devise an algorithm \textsc{OSRL-SC} whose sample complexity approaches the lower bound, and scales at most as $H(G\log(1/\delta_G)+ X\log(1/\delta_H))$,   with $X,G,H$ being, respectively, the number of tasks, representations and predictors. By comparison, this scaling is significantly better than the classical  best-arm identification algorithm that scales as $HGX\log(1/\delta)$.

On the Sample Complexity of Representation Learning in Multi-task Bandits with Global and Local structure

Decision diagrams for classification have some notable advantages over decision trees, as their internal connections can be determined at training time and their width is not bound to grow exponentially with their depth. Accordingly, decision diagrams are usually less prone to data fragmentation in internal nodes. However, the inherent complexity of training these classifiers acted as a long-standing barrier to their widespread adoption. In this context, we study the training of optimal decision diagrams (ODDs) from a mathematical programming perspective. We introduce a novel mixed-integer linear programming model for training and demonstrate its applicability for many datasets of practical importance. Further, we show how this model can be easily extended for fairness, parsimony, and stability notions. We present numerical analyses showing that our model allows training ODDs in short computational times, and that ODDs achieve better accuracy than optimal decision trees, while allowing for improved stability without significant accuracy losses.

Optimal Decision Diagrams for Classification

Despite the recent attention to DeepFakes, one of the most prevalent ways to mislead audiences on social media is the use of unaltered images in a new but false context. We propose a new method that automatically highlights out-of-context image and text pairs, for assisting fact-checkers. Our key insight is to leverage the grounding of images with text to distinguish out-of-context scenarios that cannot be disambiguated with language alone. We propose a self-supervised training strategy where we only need a set of captioned images. At train time, our method learns to selectively align individual objects in an image with textual claims, without explicit supervision. At test time, we check if both captions correspond to the same object(s) in the image but are semantically different, which allows us to make fairly accurate out-of-context predictions. Our method achieves 85% out-of-context detection accuracy. To facilitate benchmarking of this task, we create a large-scale dataset of 200K images with 450K textual captions from a variety of news websites, blogs, and social media posts

COSMOS: Catching Out-of-Context Image Misuse using Self Supervised Learning

Over the past few years, artificial intelligence (AI) has achieved great success in a variety of applications, such as image classification and recommendation systems. This suc- cess has often been achieved by training machine learning models on static datasets, where inputs and desired outputs are provided. However, we are now seeing a shift in this paradigm. Instead of learning from static datasets, machine learning models are increasingly being trained through feed- back from their interactions with the world. This is particu- larly important when machine learning models are deployed in the real world, as their decisions can often have an im- pact on other agents, turning the decision-making process into a multi-agent problem. As a result, multi-agent learning in complex environments is a critical area of research for the next generation of AI, particularly in the context of cooper- ative tasks. Cooperative multi-agent learning is an essential problem for practitioners to consider as it has the potential to enable a wide range of multi-agent tasks.
In this presentation, we will review the background and challenges of cooperative multi-agent learning. We will sur- vey our research that aims to address challenges in the fol- lowing areas:
• Scalability and cooperation in multi-agent learning, in- cluding studies on (Han et al. 2019; Du et al. 2019; Xu et al. 2020; Du et al. 2021a; Fang et al. 2019; Mguni et al. 2021). • Evaluating AI agents, including studies on (Yan et al. 2022; Du et al. 2021b).
• Human-in-the-loop interactive learning for robust and trusted decision making, including studies on (Kazantzidis et al. 2022; Gu et al. 2022; Liu et al. 2022).
• Various applications of cooperative multi-agent learning, including (Ruan et al. 2022; Xu et al. 2020; Wang et al. 2021; Chen et al. 2021).
We will also discuss future directions for research in this field.

Cooperative Multi-Agent Learning in a Complex World: Challenges and Solutions

State-space search is paramount for intelligent decision making when long-term thinking is needed. We introduce dominance and contrastive analysis methods, which enable reasoning about the relative advantages among different courses of action. This re-shapes how agents reason and leads to new families of state-space search algorithms.

Premium content

Curriculum Multi-Negative Augmentation for Debiased Video Grounding

Downloads

Next from AAAI 2023

Action-Conditioned Generation of Bimanual Object Manipulation Sequences

Similar lecture

Phrase-level Temporal Relationship Mining for Temporal Sentence Localization

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES