United States

Video copy localization aims to precisely localize all the copied segments within a pair of untrimmed videos in video retrieval applications. Previous methods typically start from frame-to-frame similarity matrix generated by cosine similarity between frame-level features of the input video pair, and then detect and refine the boundaries of copied segments on similarity matrix under temporal constraints. In this paper, we propose TransVCL: an attention-enhanced video copy localization network, which is optimized directly from initial frame-level features and trained end-to-end with three main components: a customized Transformer for feature enhancement, a correlation and softmax layer for similarity matrix generation, and a temporal alignment module for copied segments localization. In contrast to previous methods demanding the handcrafted similarity matrix, TransVCL incorporates long-range temporal information between feature sequence pair using self- and cross- attention layers. With the joint design and optimization of three components, the similarity matrix can be learned to present more discriminative copied patterns, leading to significant improvements over previous methods on segment-level labeled datasets (VCSL and VCDB). Besides the state-of-the-art performance in fully supervised setting, the attention architecture facilitates TransVCL to further exploit unlabeled or simply video-level labeled data. Additional experiments of supplementing video-level labeled datasets including SVD and FIVR reveal the high flexibility of TransVCL from full supervision to semi-supervision (with or without video-level annotation). Code is publicly available at https://github.com/transvcl/TransVCL.

AAAI 2023

TransVCL: Attention-enhanced Video Copy Localization Network with Flexible Supervision

video copy localization

cross-attention

self-attention

semi-supervision

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.

poster

Active learning (AL) aims to find a better trade-off between labeling costs and model performance by consciously selecting more informative samples to label. Recently, adversarial approaches have emerged as an effective solution to AL. Most of them leverage Generative Adversarial Networks (GAN) to align the feature distribution of labeled and unlabeled data, upon which discriminators are trained to better distinguish between them. However, these methods fail to consider the relationship between unlabeled samples and decision boundaries. Consequently, they tend to generate confused features near class boundaries, thus decreasing the ultimate performance. To address this, this paper proposes a novel adversarial AL method, namely Multi-classifier Adversarial Optimization for Active Learning (MAOAL), which trains multiple classifiers in an adversarial manner. MAOAL employs task-specific decision boundaries for data alignment while selecting the most informative samples to label. To fulfill this, we introduce a novel classifier class confusion (C3) metric, which represents the classifier discrepancy as the interclass correlation of classifier outputs. Without any additional hyper-parameters, the C3 metric further reduces the negative impacts of ambiguous samples in the process of distribution alignment and sample selection. More concretely, the network is trained adversarially by adding two auxiliary classifiers, reducing the distribution bias of labeled and unlabeled samples by minimizing the C3 loss between classifiers, while learning tighter decision boundaries and highlighting hard samples by maximizing the C3 loss. Finally, the unlabeled samples with the highest C3 loss are selected for labeling. Extensive experimental results demonstrate the superiority of our approach over state-of-the-art AL methods in terms of both image classification and object detection tasks.



Multi-classifier Adversarial Optimization for¬†Active Learning

In this paper, we study the problem of MOOC quality evaluation that is essential for improving the course materials, promoting students' learning efficiency, and benefiting user services. 
While achieving promising performances, current works still suffer from the complicated interactions and relationships of entities in MOOC platforms. 
To tackle the challenges, we formulate the problem as a course representation learning task based, and develop an Information-aware Graph Representation Learning(IaGRL) for multi-view MOOC quality evaluation. 
Specifically, We first build a MOOC Heterogeneous Network (HIN) to represent the interactions and relationships among entities in MOOC platforms. 
And then we decompose the MOOC HIN into multiple single-relation graphs based on meta-paths to depict multi-view semantics of courses. 
The course representation learning can be further converted to a multi-view graph representation task. 
Different from traditional graph representation learning, the learned course representations are expected to match the following three types of validity: 
(1) the agreement on expressiveness between the raw course portfolio and the learned course representations; 
(2) the consistency between the representations in each view and the unified representations; 
(3) the alignment between the course and MOOC platform representations. 
Therefore, we propose to exploit mutual information for preserving the validity of course representations. 
We conduct extensive experiments over real-world MOOC datasets to demonstrate the effectiveness of our proposed method.


Multi-View MOOC Quality Evaluation via Information-Aware Graph Representation Learning

In this work, we are dedicated to leveraging the BERT pre-training success and modeling the domain-specific statistics to fertilize the sign language recognition~(SLR) model. Considering the dominance of hand and body in sign language expression, we organize them as pose triplet units and feed them into the Transformer backbone in a frame-wise manner. Pre-training is performed via reconstructing the masked triplet unit from the corrupted input sequence, which learns the hierarchical correlation context cues among internal and external triplet units. Notably, different from the highly semantic word token in BERT, the pose unit is a low-level signal originally locating in continuous space, which prevents the direct adoption of the BERT cross entropy objective. To this end, we bridge this semantic gap via coupling tokenization of the triplet unit. It adaptively extracts the discrete pseudo label from the pose triplet unit, which represents the semantic gesture / body state. After pre-training, we fine-tune the pre-trained encoder on the downstream SLR task, jointly with the newly added task-specific layer. Extensive experiments are conducted to validate the effectiveness of our proposed method, achieving new state-of-the-art performance on all four benchmarks with a notable gain.

BEST: BERT Pre-Training for Sign Language Recognition with Coupling Tokenization

While graph neural networks (GNNs) have achieved notable success in various graph mining tasks, conventional GNNs only consider the pairwise correlation in 1-hop neighbors without considering the long-term relations and the high-order patterns, thus limiting their performances. Therefore, several previous works explore the motif, i.e., the frequent high-order subgraphs, to exploit the high-order structure on the graph. However, motif-based methods usually require an unacceptable computational time to enumerate all possible combinations on the graph. As a promising method to discover the graph structure, we introduce a new GNN framework, namely Random Walk Conformer (RWC), to model both global correlations and local patterns from motifs based on the random walk. Besides, we propose random walk encoding to help RWC capture topological information, which is proven to be more expressive than conventional spatial encoding. Extensive experiment results manifest that RWC achieves state-of-the-art performance on graph classification and regression tasks.

Random Walk Conformer: Learning Graph Representation from Long and Short Range

Deep Entity Matching (EM) is one of the core research topics in data integration. Typical existing works construct EM models by training deep neural networks (DNNs) based on the training samples with onehot labels. However, these sharp supervision signals of onehot labels harm the generalization of EM models, causing them to overfit the training samples and perform badly in unseen datasets. To solve this problem, we first propose that the challenge of training a well-generalized EM model lies in achieving the compromise between fitting the training samples and imposing regularization, i.e., the bias-variance tradeoff. Then, we propose a novel Soft Target-EnhAnced Matching (Steam) framework, which exploits the automatically generated soft targets as label-wise regularizers to constrain the model training. Specifically, Steam regards the EM model trained in previous iteration as a virtual teacher and takes its softened output as the extra regularizer to train the EM model in the current iteration. As such, Steam effectively calibrates the obtained EM model, achieving the bias-variance tradeoff without any additional computational cost. We conduct extensive experiments over open datasets and the results show that our proposed Steam outperforms the state-of-the-art EM approaches in terms of effectiveness and label efficiency.

Soft Target-enhanced Matching Framework for Deep Entity Matching

Synthesizing controllable motion for a character using deep learning has been a promising approach due to its potential to learn a compact model without laborious feature engineering. To produce dynamic motion from weak control signals such as desired paths, existing methods often require auxiliary information such as phases for alleviating motion ambiguity, which limits their generalisation capability. As past poses often contain useful auxiliary hints, in this paper, we propose a task-agnostic deep learning method, namely Multi-scale Control Signal-aware Transformer (MCS-T), with an attention based encoder-decoder architecture to discover the auxiliary information implicitly for synthesizing controllable motion without explicitly requiring auxiliary information such as phase. Specifically, an encoder is devised to adaptively formulate the motion patterns of a character's past poses with multi-scale skeletons, and  a decoder driven by control signals to further synthesize and predict the character's state by paying context-specialised attention to the encoded past motion patterns. As a result, it helps alleviate the issues of low responsiveness and slow transition which often happen in conventional methods not using auxiliary information. Both qualitative and quantitative experimental results on an existing biped locomotion dataset, which involves diverse types of motion transitions, demonstrate the effectiveness of our method. In particular, MCS-T is able to successfully generate motions comparable to those generated by the methods using auxiliary information.

Multi-Scale Control Signal-Aware Transformer for Motion Synthesis without Phase

Selecting a committee that meets diversity and proportionality criteria is a challenging endeavor that has been studied extensively in recent years. This task becomes even more challenging when some of the selected candidates decline the invitation to join the committee. Since the unavailability of one candidate may impact the rest of the selection, inviting all candidates at the same time may lead to a suboptimal committee. Instead, invitations should be sequential and conditional on which candidates invited so far accepted the invitation: the solution to the committee selection problem is a query policy. If invitation queries are binding, they should be safe: one should not query a candidate without being sure that whatever the set of available candidates possible at that stage, her inclusion will not jeopardize committee optimality. Assuming approval-based inputs, we characterize the set of rules for which a safe query exists at every stage. In order to parallelize the invitation process, we investigate the computation of safe parallel queries, and show that it is often hard. We also study the existence of safe parallel queries with respect to proportionality axioms such as extended justified representation.

Multiwinner Voting with Possibly Unavailable Candidates

A cornerstone in AI research has been the creation and adoption of standardized training and test datasets to earmark the progress of state-of-the-art models. A particularly successful example is the GLUE dataset for training and evaluating Natural Language Understanding (NLU) models for English. The large body of research around self-supervised BERT-based language models revolved around performance improvements on NLU tasks in GLUE. To evaluate language models in other languages, several language-specific GLUE datasets were created. The area of speech language understanding (SLU) has followed a similar trajectory. The success of large self-supervised models such as wav2vec2 enable creation of speech models with relatively easy to access unlabelled data. These models can then be evaluated on SLU tasks, such as the SUPERB benchmark. In this work, we extend this to Indic languages by releasing the IndicSUPERB benchmark. Specifically, we make the following three contributions. (i) We collect Kathbath containing 1,684 hours of labelled speech data across 12 Indian languages from 1,218 contributors located in 203 districts in India. (ii) Using Kathbath, we create benchmarks across 6 speech tasks: Automatic Speech Recognition, Speaker Verification, Speaker Identification (mono/multi), Language Identification, Query By Example, and Keyword Spotting for 12 languages. (iii) On the released benchmarks, we train and evaluate different self-supervised models alongside the a commonly used baseline FBANK. We show that language-specific fine-tuned models are more accurate than baseline on most of the tasks, including a large gap of 76% for Language Identification task. However, for speaker identification, self-supervised models trained on large datasets demonstrate an advantage. We hope IndicSUPERB contributes to the progress of developing speech language understanding models for Indian languages. 

IndicSUPERB: A Speech processing Universal Performance Benchmark for Indian languages

We develop the first fully dynamic algorithm that maintains a decision tree over an arbitrary sequence of insertions and deletions of labeled examples. Given $\epsilon > 0$ our algorithm guarantees that, at every point in time, every node of the decision tree uses a split with Gini gain within an additive $\epsilon$ of the optimum. For real-valued features the algorithm has an amortized running time per insertion/deletion of $O\big(\frac{d \log^3 n}{\epsilon^2})$, which improves to $O\big(\frac{d \log^2 n}{\epsilon})$ for binary or categorical features, and uses space $O(n d)$, where $n$ is the maximum number of examples at any point in time and $d$ is the number of features. Our algorithm is nearly optimal, as we show that any algorithm with similar guarantees uses amortized running time $\Omega(d)$ and space $\widetilde {\Omega} (n d)$. We complement our theoretical results with an extensive experimental evaluation on real-world data, showing the effectiveness of our algorithm. 

Fully-Dynamic Decision Trees

To date, little attention has been given to multi-view 3D human mesh estimation, despite real-life applicability (e.g., motion capture, sport analysis) and robustness to single-view ambiguities. Existing solutions typically suffer from poor generalization performance to new settings, largely due to the limited diversity of image/3D-mesh pairs in multi-view training data. To address this shortcoming, people have explored the use of synthetic images. But besides the usual impact of visual gap between rendered and target data, synthetic-data-driven multi-view estimators also suffer from overfitting to the camera viewpoint distribution sampled during training which usually differs from real-world distributions. Tackling both challenges, we propose a novel simulation-based training pipeline for multi-view human mesh recovery, which (a) relies on intermediate 2D representations which are more robust to synthetic-to-real domain gap; (b) leverages learnable calibration and triangulation to adapt to more diversified camera setups; and (c) progressively aggregates multi-view information in a canonical 3D space to remove ambiguities in 2D representations. Through extensive benchmarking, we demonstrate the superiority of the proposed solution especially for unseen in-the-wild scenarios. 

Premium content

TransVCL: Attention-enhanced Video Copy Localization Network with Flexible Supervision

Downloads

Next from AAAI 2023

Multi-classifier Adversarial Optimization for¬†Active Learning

Similar lecture

SeDepTTSÔºö Enhancing the Naturalness via Semantic Dependency and Local Convolution for Text-to-Speech Synthesis