Yuexian Zou

Xinhao Mei, Chutong Meng, Haohe Liu et al.

The advancement of audio-language (AL) multimodal learning tasks has been significant in recent years. However, researchers face challenges due to the costly and time-consuming collection process of existing audio-language datasets, which are limited in size. To address this data scarcity issue, we introduce WavCaps, the first large-scale weakly-labelled audio captioning dataset, comprising approximately 400k audio clips with paired captions. We sourced audio clips and their raw descriptions from web sources and a sound event detection dataset. However, the online-harvested raw descriptions are highly noisy and unsuitable for direct use in tasks such as automated audio captioning. To overcome this issue, we propose a three-stage processing pipeline for filtering noisy data and generating high-quality captions, where ChatGPT, a large language model, is leveraged to filter and transform raw descriptions automatically. We conduct a comprehensive analysis of the characteristics of WavCaps dataset and evaluate it on multiple downstream audio-language multimodal learning tasks. The systems trained on WavCaps outperform previous state-of-the-art (SOTA) models by a significant margin. Our aspiration is for the WavCaps dataset we have proposed to facilitate research in audio-language multimodal learning and demonstrate the potential of utilizing ChatGPT to enhance academic research. Our dataset and codes are available at https://github.com/XinhaoMei/WavCaps.

Ziyu Yao, Xuxin Cheng, Yuexian Zou · pku

This paper presents a significant contribution to the field of repetitive action counting through the introduction of a new approach called Pose Saliency Representation. The proposed method efficiently represents each action using only two salient poses instead of redundant frames, which significantly reduces the computational cost while improving the performance. Moreover, we introduce a pose-level method, PoseRAC, which is based on this representation and achieves state-of-the-art performance on two new version datasets by using Pose Saliency Annotation to annotate salient poses for training. Our lightweight model is highly efficient, requiring only 20 minutes for training on a GPU, and infers nearly 10x faster compared to previous methods. In addition, our approach achieves a substantial improvement over the previous state-of-the-art TransRAC, achieving an OBO metric of 0.56 compared to 0.29 of TransRAC. The code and new dataset are available at https://github.com/MiracleDance/PoseRAC for further research and experimentation, making our proposed approach highly accessible to the research community.

Dongchao Yang, Jianwei Yu, Helin Wang et al.

Generating sound effects that humans want is an important topic. However, there are few studies in this area for sound generation. In this study, we investigate generating sound conditioned on a text prompt and propose a novel text-to-sound generation framework that consists of a text encoder, a Vector Quantized Variational Autoencoder (VQ-VAE), a decoder, and a vocoder. The framework first uses the decoder to transfer the text features extracted from the text encoder to a mel-spectrogram with the help of VQ-VAE, and then the vocoder is used to transform the generated mel-spectrogram into a waveform. We found that the decoder significantly influences the generation performance. Thus, we focus on designing a good decoder in this study. We begin with the traditional autoregressive decoder, which has been proved as a state-of-the-art method in previous sound generation works. However, the AR decoder always predicts the mel-spectrogram tokens one by one in order, which introduces the unidirectional bias and accumulation of errors problems. Moreover, with the AR decoder, the sound generation time increases linearly with the sound duration. To overcome the shortcomings introduced by AR decoders, we propose a non-autoregressive decoder based on the discrete diffusion model, named Diffsound. Specifically, the Diffsound predicts all of the mel-spectrogram tokens in one step and then refines the predicted tokens in the next step, so the best-predicted results can be obtained after several steps. Our experiments show that our proposed Diffsound not only produces better text-to-sound generation results when compared with the AR decoder but also has a faster generation speed, e.g., MOS: 3.56 \textit{v.s} 2.786, and the generation speed is five times faster than the AR decoder.

Bang Yang, Fenglin Liu, Xian Wu et al.

Supervised visual captioning models typically require a large scale of images or videos paired with descriptions in a specific language (i.e., the vision-caption pairs) for training. However, collecting and labeling large-scale datasets is time-consuming and expensive for many scenarios and languages. Therefore, sufficient labeled pairs are usually not available. To deal with the label shortage problem, we present a simple yet effective zero-shot approach MultiCapCLIP that can generate visual captions for different scenarios and languages without any labeled vision-caption pairs of downstream datasets. In the training stage, MultiCapCLIP only requires text data for input. Then it conducts two main steps: 1) retrieving concept prompts that preserve the corresponding domain knowledge of new scenarios; 2) auto-encoding the prompts to learn writing styles to output captions in a desired language. In the testing stage, MultiCapCLIP instead takes visual data as input directly to retrieve the concept prompts to generate the final visual descriptions. The extensive experiments on image and video captioning across four benchmarks and four languages (i.e., English, Chinese, German, and French) confirm the effectiveness of our approach. Compared with state-of-the-art zero-shot and weakly-supervised methods, our method achieves 4.8% and 21.5% absolute improvements in terms of BLEU@4 and CIDEr metrics. Our code is available at https://github.com/yangbang18/MultiCapCLIP.

Can Zhang, Tianyu Yang, Junwu Weng et al.

Unsupervised video representation learning has made remarkable achievements in recent years. However, most existing methods are designed and optimized for video classification. These pre-trained models can be sub-optimal for temporal localization tasks due to the inherent discrepancy between video-level classification and clip-level localization. To bridge this gap, we make the first attempt to propose a self-supervised pretext task, coined as Pseudo Action Localization (PAL) to Unsupervisedly Pre-train feature encoders for Temporal Action Localization tasks (UP-TAL). Specifically, we first randomly select temporal regions, each of which contains multiple clips, from one video as pseudo actions and then paste them onto different temporal positions of the other two videos. The pretext task is to align the features of pasted pseudo action regions from two synthetic videos and maximize the agreement between them. Compared to the existing unsupervised video representation learning approaches, our PAL adapts better to downstream TAL tasks by introducing a temporal equivariant contrastive learning paradigm in a temporally dense and scale-aware manner. Extensive experiments show that PAL can utilize large-scale unlabeled video data to significantly boost the performance of existing TAL methods. Our codes and models will be made publicly available at https://github.com/zhang-can/UP-TAL.

Fenglin Liu, Xuancheng Ren, Xian Wu et al. · oxford

Recently, attention based models have been used extensively in many sequence-to-sequence learning systems. Especially for image captioning, the attention based models are expected to ground correct image regions with proper generated words. However, for each time step in the decoding process, the attention based models usually use the hidden state of the current input to attend to the image regions. Under this setting, these attention models have a "deviated focus" problem that they calculate the attention weights based on previous words instead of the one to be generated, impairing the performance of both grounding and captioning. In this paper, we propose the Prophet Attention, similar to the form of self-supervision. In the training stage, this module utilizes the future information to calculate the "ideal" attention weights towards image regions. These calculated "ideal" weights are further used to regularize the "deviated" attention. In this manner, image regions are grounded with the correct words. The proposed Prophet Attention can be easily incorporated into existing image captioning models to improve their performance of both grounding and captioning. The experiments on the Flickr30k Entities and the MSCOCO datasets show that the proposed Prophet Attention consistently outperforms baselines in both automatic metrics and human evaluations. It is worth noticing that we set new state-of-the-arts on the two benchmark datasets and achieve the 1st place on the leaderboard of the online MSCOCO benchmark in terms of the default ranking score, i.e., CIDEr-c40.

Chenyu You, Nuo Chen, Fenglin Liu et al. · oxford

In spoken question answering, the systems are designed to answer questions from contiguous text spans within the related speech transcripts. However, the most natural way that human seek or test their knowledge is via human conversations. Therefore, we propose a new Spoken Conversational Question Answering task (SCQA), aiming at enabling the systems to model complex dialogue flows given the speech documents. In this task, our main objective is to build the system to deal with conversational questions based on the audio recordings, and to explore the plausibility of providing more cues from different modalities with systems in information gathering. To this end, instead of directly adopting automatically generated speech transcripts with highly noisy data, we propose a novel unified data distillation approach, DDNet, which effectively ingests cross-modal information to achieve fine-grained representations of the speech and language modalities. Moreover, we propose a simple and novel mechanism, termed Dual Attention, by encouraging better alignments between audio and text to ease the process of knowledge transfer. To evaluate the capacity of SCQA systems in a dialogue-style interaction, we assemble a Spoken Conversational Question Answering (Spoken-CoQA) dataset with more than 40k question-answer pairs from 4k conversations. The performance of the existing state-of-the-art methods significantly degrade on our dataset, hence demonstrating the necessity of cross-modal information integration. Our experimental results demonstrate that our proposed method achieves superior performance in spoken conversational question answering tasks.

Bang Yang, Fenglin Liu, Yuexian Zou et al. · oxford

Natural Language Generation (NLG) accepts input data in the form of images, videos, or text and generates corresponding natural language text as output. Existing NLG methods mainly adopt a supervised approach and rely heavily on coupled data-to-text pairs. However, for many targeted scenarios and for non-English languages, sufficient quantities of labeled data are often not available. To relax the dependency on labeled data of downstream tasks, we propose an intuitive and effective zero-shot learning framework, ZeroNLG, which can deal with multiple NLG tasks, including image-to-text (image captioning), video-to-text (video captioning), and text-to-text (neural machine translation), across English, Chinese, German, and French within a unified framework. ZeroNLG does not require any labeled downstream pairs for training. During training, ZeroNLG (i) projects different domains (across modalities and languages) to corresponding coordinates in a shared common latent space; (ii) bridges different domains by aligning their corresponding coordinates in this space; and (iii) builds an unsupervised multilingual auto-encoder to learn to generate text by reconstructing the input text given its coordinate in shared latent space. Consequently, during inference, based on the data-to-text pipeline, ZeroNLG can generate target sentences across different languages given the coordinate of input data in the common space. Within this unified framework, given visual (imaging or video) data as input, ZeroNLG can perform zero-shot visual captioning; given textual sentences as input, ZeroNLG can perform zero-shot machine translation. We present the results of extensive experiments on twelve NLG tasks, showing that, without using any labeled downstream pairs for training, ZeroNLG generates high-quality and believable outputs and significantly outperforms existing zero-shot methods.

Fenglin Liu, Xian Wu, Chenyu You et al. · oxford

Training supervised video captioning model requires coupled video-caption pairs. However, for many targeted languages, sufficient paired data are not available. To this end, we introduce the unpaired video captioning task aiming to train models without coupled video-caption pairs in target language. To solve the task, a natural choice is to employ a two-step pipeline system: first utilizing video-to-pivot captioning model to generate captions in pivot language and then utilizing pivot-to-target translation model to translate the pivot captions to the target language. However, in such a pipeline system, 1) visual information cannot reach the translation model, generating visual irrelevant target captions; 2) the errors in the generated pivot captions will be propagated to the translation model, resulting in disfluent target captions. To address these problems, we propose the Unpaired Video Captioning with Visual Injection system (UVC-VI). UVC-VI first introduces the Visual Injection Module (VIM), which aligns source visual and target language domains to inject the source visual information into the target language domain. Meanwhile, VIM directly connects the encoder of the video-to-pivot model and the decoder of the pivot-to-target model, allowing end-to-end inference by completely skipping the generation of pivot captions. To enhance the cross-modality injection of the VIM, UVC-VI further introduces a pluggable video encoder, i.e., Multimodal Collaborative Encoder (MCE). The experiments show that UVC-VI outperforms pipeline systems and exceeds several supervised systems. Furthermore, equipping existing supervised systems with our MCE can achieve 4% and 7% relative margins on the CIDEr scores to current state-of-the-art models on the benchmark MSVD and MSR-VTT datasets, respectively.

Fenglin Liu, Xian Wu, Shen Ge et al. · oxford

Vision-and-language (V-L) tasks require the system to understand both vision content and natural language, thus learning fine-grained joint representations of vision and language (a.k.a. V-L representations) is of paramount importance. Recently, various pre-trained V-L models are proposed to learn V-L representations and achieve improved results in many tasks. However, the mainstream models process both vision and language inputs with the same set of attention matrices. As a result, the generated V-L representations are entangled in one common latent space. To tackle this problem, we propose DiMBERT (short for Disentangled Multimodal-Attention BERT), which is a novel framework that applies separated attention spaces for vision and language, and the representations of multi-modalities can thus be disentangled explicitly. To enhance the correlation between vision and language in disentangled spaces, we introduce the visual concepts to DiMBERT which represent visual information in textual format. In this manner, visual concepts help to bridge the gap between the two modalities. We pre-train DiMBERT on a large amount of image-sentence pairs on two tasks: bidirectional language modeling and sequence-to-sequence language modeling. After pre-train, DiMBERT is further fine-tuned for the downstream tasks. Experiments show that DiMBERT sets new state-of-the-art performance on three tasks (over four datasets), including both generation tasks (image captioning and visual storytelling) and classification tasks (referring expressions). The proposed DiM (short for Disentangled Multimodal-Attention) module can be easily incorporated into existing pre-trained V-L models to boost their performance, up to a 5% increase on the representative task. Finally, we conduct a systematic analysis and demonstrate the effectiveness of our DiM and the introduced visual concepts.

Bowen Cao, Qichen Ye, Weiyuan Xu et al.

Learning representations for graph-structured data is essential for graph analytical tasks. While remarkable progress has been made on static graphs, researches on temporal graphs are still in its beginning stage. The bottleneck of the temporal graph representation learning approach is the neighborhood aggregation strategy, based on which graph attributes share and gather information explicitly. Existing neighborhood aggregation strategies fail to capture either the short-term features or the long-term features of temporal graph attributes, leading to unsatisfactory model performance and even poor robustness and domain generality of the representation learning method. To address this problem, we propose a Frame-level Timeline Modeling (FTM) method that helps to capture both short-term and long-term features and thus learns more informative representations on temporal graphs. In particular, we present a novel link-based framing technique to preserve the short-term features and then incorporate a timeline aggregator module to capture the intrinsic dynamics of graph evolution as long-term features. Our method can be easily assembled with most temporal GNNs. Extensive experiments on common datasets show that our method brings great improvements to the capability, robustness, and domain generality of backbone methods in downstream tasks. Our code can be found at https://github.com/yeeeqichen/FTM.

Jinchuan Tian, Jianwei Yu, Chao Weng et al.

In automatic speech recognition (ASR) research, discriminative criteria have achieved superior performance in DNN-HMM systems. Given this success, the adoption of discriminative criteria is promising to boost the performance of end-to-end (E2E) ASR systems. With this motivation, previous works have introduced the minimum Bayesian risk (MBR, one of the discriminative criteria) into E2E ASR systems. However, the effectiveness and efficiency of the MBR-based methods are compromised: the MBR criterion is only used in system training, which creates a mismatch between training and decoding; the on-the-fly decoding process in MBR-based methods results in the need for pre-trained models and slow training speeds. To this end, novel algorithms are proposed in this work to integrate another widely used discriminative criterion, lattice-free maximum mutual information (LF-MMI), into E2E ASR systems not only in the training stage but also in the decoding process. The proposed LF-MMI training and decoding methods show their effectiveness on two widely used E2E frameworks: Attention-Based Encoder-Decoders (AEDs) and Neural Transducers (NTs). Compared with MBR-based methods, the proposed LF-MMI method: maintains the consistency between training and decoding; eschews the on-the-fly decoding process; trains from randomly initialized models with superior training efficiency. Experiments suggest that the LF-MMI method outperforms its MBR counterparts and consistently leads to statistically significant performance improvements on various frameworks and datasets from 30 hours to 14.3k hours. The proposed method achieves state-of-the-art (SOTA) results on Aishell-1 (CER 4.10%) and Aishell-2 (CER 5.02%) datasets. Code is released.

Yifei Xin, Dongchao Yang, Fan Cui et al. · pku

Existing weakly supervised sound event detection (WSSED) work has not explored both types of co-occurrences simultaneously, i.e., some sound events often co-occur, and their occurrences are usually accompanied by specific background sounds, so they would be inevitably entangled, causing misclassification and biased localization results with only clip-level supervision. To tackle this issue, we first establish a structural causal model (SCM) to reveal that the context is the main cause of co-occurrence confounders that mislead the model to learn spurious correlations between frames and clip-level labels. Based on the causal analysis, we propose a causal intervention (CI) method for WSSED to remove the negative impact of co-occurrence confounders by iteratively accumulating every possible context of each class and then re-projecting the contexts to the frame-level features for making the event boundary clearer. Experiments show that our method effectively improves the performance on multiple datasets and can generalize to various baseline models.

Meng Cao, Tianyu Yang, Junwu Weng et al.

Video-Text Pre-training (VTP) aims to learn transferable representations for various downstream tasks from large-scale web videos. To date, almost all existing VTP methods are limited to retrieval-based downstream tasks, e.g., video retrieval, whereas their transfer potentials on localization-based tasks, e.g., temporal grounding, are under-explored. In this paper, we experimentally analyze and demonstrate the incompatibility of current VTP methods with localization tasks, and propose a novel Localization-oriented Video-Text Pre-training framework, dubbed as LocVTP. Specifically, we perform the fine-grained contrastive alignment as a complement to the coarse-grained one by a clip-word correspondence discovery scheme. To further enhance the temporal reasoning ability of the learned feature, we propose a context projection head and a temporal aware contrastive loss to perceive the contextual relationships. Extensive experiments on four downstream tasks across six datasets demonstrate that our LocVTP achieves state-of-the-art performance on both retrieval-based and localization-based tasks. Furthermore, we conduct comprehensive ablation studies and thorough analyses to explore the optimum model designs and training strategies.

Xuxin Cheng, Qianqian Dong, Fengpeng Yue et al.

How to solve the data scarcity problem for end-to-end speech-to-text translation (ST)? It's well known that data augmentation is an efficient method to improve performance for many tasks by enlarging the dataset. In this paper, we propose Mix at three levels for Speech Translation (M^3ST) method to increase the diversity of the augmented training corpus. Specifically, we conduct two phases of fine-tuning based on a pre-trained model using external machine translation (MT) data. In the first stage of fine-tuning, we mix the training corpus at three levels, including word level, sentence level and frame level, and fine-tune the entire model with mixed data. At the second stage of fine-tuning, we take both original speech sequences and original text sequences in parallel into the model to fine-tune the network, and use Jensen-Shannon divergence to regularize their outputs. Experiments on MuST-C speech translation benchmark and analysis show that M^3ST outperforms current strong baselines and achieves state-of-the-art results on eight directions with an average BLEU of 29.9.

Yaowei Li, Bang Yang, Xuxin Cheng et al.

Automatic radiology report generation has attracted enormous research interest due to its practical value in reducing the workload of radiologists. However, simultaneously establishing global correspondences between the image (e.g., Chest X-ray) and its related report and local alignments between image patches and keywords remains challenging. To this end, we propose an Unify, Align and then Refine (UAR) approach to learn multi-level cross-modal alignments and introduce three novel modules: Latent Space Unifier (LSU), Cross-modal Representation Aligner (CRA) and Text-to-Image Refiner (TIR). Specifically, LSU unifies multimodal data into discrete tokens, making it flexible to learn common knowledge among modalities with a shared network. The modality-agnostic CRA learns discriminative features via a set of orthonormal basis and a dual-gate mechanism first and then globally aligns visual and textual representations under a triplet contrastive loss. TIR boosts token-level local alignment via calibrating text-to-image attention with a learnable mask. Additionally, we design a two-stage training procedure to make UAR gradually grasp cross-modal alignments at different levels, which imitates radiologists' workflow: writing sentence by sentence first and then checking word by word. Extensive experiments and analyses on IU-Xray and MIMIC-CXR benchmark datasets demonstrate the superiority of our UAR against varied state-of-the-art methods.

Meng Cao, Ji Jiang, Long Chen et al.

We investigate the problem of video Referring Expression Comprehension (REC), which aims to localize the referent objects described in the sentence to visual regions in the video frames. Despite the recent progress, existing methods suffer from two problems: 1) inconsistent localization results across video frames; 2) confusion between the referent and contextual objects. To this end, we propose a novel Dual Correspondence Network (dubbed as DCNet) which explicitly enhances the dense associations in both the inter-frame and cross-modal manners. Firstly, we aim to build the inter-frame correlations for all existing instances within the frames. Specifically, we compute the inter-frame patch-wise cosine similarity to estimate the dense alignment and then perform the inter-frame contrastive learning to map them close in feature space. Secondly, we propose to build the fine-grained patch-word alignment to associate each patch with certain words. Due to the lack of this kind of detailed annotations, we also predict the patch-word correspondence through the cosine similarity. Extensive experiments demonstrate that our DCNet achieves state-of-the-art performance on both video and image REC benchmarks. Furthermore, we conduct comprehensive ablation studies and thorough analyses to explore the optimal model designs. Notably, our inter-frame and cross-modal contrastive losses are plug-and-play functions and are applicable to any video REC architectures. For example, by building on top of Co-grounding, we boost the performance by 1.48% absolute improvement on Accu.@0.5 for VID-Sentence dataset.

Jinchuan Tian, Jianwei Yu, Chunlei Zhang et al.

Despite the rapid progress in automatic speech recognition (ASR) research, recognizing multilingual speech using a unified ASR system remains highly challenging. Previous works on multilingual speech recognition mainly focus on two directions: recognizing multiple monolingual speech or recognizing code-switched speech that uses different languages interchangeably within a single utterance. However, a pragmatic multilingual recognizer is expected to be compatible with both directions. In this work, a novel language-aware encoder (LAE) architecture is proposed to handle both situations by disentangling language-specific information and generating frame-level language-aware representations during encoding. In the LAE, the primary encoding is implemented by the shared block while the language-specific blocks are used to extract specific representations for each language. To learn language-specific information discriminatively, a language-aware training method is proposed to optimize the language-specific blocks in LAE. Experiments conducted on Mandarin-English code-switched speech suggest that the proposed LAE is capable of discriminating different languages in frame-level and shows superior performance on both monolingual and multilingual ASR tasks. With either a real-recorded or simulated code-switched dataset, the proposed LAE achieves statistically significant improvements on both CTC and neural transducer systems. Code is released

Hongxiang Li, Meng Cao, Xuxin Cheng et al.

The recent video grounding works attempt to introduce vanilla contrastive learning into video grounding. However, we claim that this naive solution is suboptimal. Contrastive learning requires two key properties: (1) \emph{alignment} of features of similar samples, and (2) \emph{uniformity} of the induced distribution of the normalized features on the hypersphere. Due to two annoying issues in video grounding: (1) the co-existence of some visual entities in both ground truth and other moments, \ie semantic overlapping; (2) only a few moments in the video are annotated, \ie sparse annotation dilemma, vanilla contrastive learning is unable to model the correlations between temporally distant moments and learned inconsistent video representations. Both characteristics lead to vanilla contrastive learning being unsuitable for video grounding. In this paper, we introduce Geodesic and Game Localization (G2L), a semantically aligned and uniform video grounding framework via geodesic and game theory. We quantify the correlations among moments leveraging the geodesic distance that guides the model to learn the correct cross-modal representations. Furthermore, from the novel perspective of game theory, we propose semantic Shapley interaction based on geodesic distance sampling to learn fine-grained semantic alignment in similar moments. Experiments on three benchmarks demonstrate the effectiveness of our method.

Xuxin Cheng, Bowen Cao, Qichen Ye et al.

Spoken language understanding (SLU) is a fundamental task in the task-oriented dialogue systems. However, the inevitable errors from automatic speech recognition (ASR) usually impair the understanding performance and lead to error propagation. Although there are some attempts to address this problem through contrastive learning, they (1) treat clean manual transcripts and ASR transcripts equally without discrimination in fine-tuning; (2) neglect the fact that the semantically similar pairs are still pushed away when applying contrastive learning; (3) suffer from the problem of Kullback-Leibler (KL) vanishing. In this paper, we propose Mutual Learning and Large-Margin Contrastive Learning (ML-LMCL), a novel framework for improving ASR robustness in SLU. Specifically, in fine-tuning, we apply mutual learning and train two SLU models on the manual transcripts and the ASR transcripts, respectively, aiming to iteratively share knowledge between these two models. We also introduce a distance polarization regularizer to avoid pushing away the intra-cluster pairs as much as possible. Moreover, we use a cyclical annealing schedule to mitigate KL vanishing issue. Experiments on three datasets show that ML-LMCL outperforms existing models and achieves new state-of-the-art performance.

Zhihong Zhu, Weiyuan Xu, Xuxin Cheng et al.

Multi-intent detection and slot filling joint models are gaining increasing traction since they are closer to complicated real-world scenarios. However, existing approaches (1) focus on identifying implicit correlations between utterances and one-hot encoded labels in both tasks while ignoring explicit label characteristics; (2) directly incorporate multi-intent information for each token, which could lead to incorrect slot prediction due to the introduction of irrelevant intent. In this paper, we propose a framework termed DGIF, which first leverages the semantic information of labels to give the model additional signals and enriched priors. Then, a multi-grain interactive graph is constructed to model correlations between intents and slots. Specifically, we propose a novel approach to construct the interactive graph based on the injection of label semantics, which can automatically update the graph to better alleviate error propagation. Experimental results show that our framework significantly outperforms existing approaches, obtaining a relative improvement of 13.7% over the previous best model on the MixATIS dataset in overall accuracy.

Qichen Ye, Bowen Cao, Nuo Chen et al.

Knowledge-aware question answering (KAQA) requires the model to answer questions over a knowledge base, which is essential for both open-domain QA and domain-specific QA, especially when language models alone cannot provide all the knowledge needed. Despite the promising result of recent KAQA systems which tend to integrate linguistic knowledge from pre-trained language models (PLM) and factual knowledge from knowledge graphs (KG) to answer complex questions, a bottleneck exists in effectively fusing the representations from PLMs and KGs because of (i) the semantic and distributional gaps between them, and (ii) the difficulties in joint reasoning over the provided knowledge from both modalities. To address the above two problems, we propose a Fine-grained Two-stage training framework (FiTs) to boost the KAQA system performance: The first stage aims at aligning representations from the PLM and the KG, thus bridging the modality gaps between them, named knowledge adaptive post-training. The second stage, called knowledge-aware fine-tuning, aims to improve the model's joint reasoning ability based on the aligned representations. In detail, we fine-tune the post-trained model via two auxiliary self-supervised tasks in addition to the QA supervision. Extensive experiments demonstrate that our approach achieves state-of-the-art performance on three benchmarks in the commonsense reasoning (i.e., CommonsenseQA, OpenbookQA) and medical question answering (i.e., MedQA-USMILE) domains.

Hongxiang Li, Meng Cao, Xuxin Cheng et al.

Video grounding aims to locate a moment of interest matching the given query sentence from an untrimmed video. Previous works ignore the {sparsity dilemma} in video annotations, which fails to provide the context information between potential events and query sentences in the dataset. In this paper, we contend that exploiting easily available captions which describe general actions, i.e., auxiliary captions defined in our paper, will significantly boost the performance. To this end, we propose an Auxiliary Caption Network (ACNet) for video grounding. Specifically, we first introduce dense video captioning to generate dense captions and then obtain auxiliary captions by Non-Auxiliary Caption Suppression (NACS). To capture the potential information in auxiliary captions, we propose Caption Guided Attention (CGA) project the semantic relations between auxiliary captions and query sentences into temporal space and fuse them into visual representations. Considering the gap between auxiliary captions and ground truth, we propose Asymmetric Cross-modal Contrastive Learning (ACCL) for constructing more negative pairs to maximize cross-modal mutual information. Extensive experiments on three public datasets (i.e., ActivityNet Captions, TACoS and ActivityNet-CG) demonstrate that our method significantly outperforms state-of-the-art methods.

Bang Yang, Asif Raza, Yuexian Zou et al.

Medical caption prediction which can be regarded as a task of medical report generation (MRG), requires the automatic generation of coherent and accurate captions for the given medical images. However, the scarcity of labelled medical image-report pairs presents great challenges in the development of deep and large-scale neural networks capable of harnessing the potential artificial general intelligence power like large language models (LLMs). In this work, we propose customizing off-the-shelf general-purpose large-scale pre-trained models, i.e., foundation models (FMs), in computer vision and natural language processing with a specific focus on medical report generation. Specifically, following BLIP-2, a state-of-the-art vision-language pre-training approach, we introduce our encoder-decoder-based MRG model. This model utilizes a lightweight query Transformer to connect two FMs: the giant vision Transformer EVA-ViT-g and a bilingual LLM trained to align with human intentions (referred to as ChatGLM-6B). Furthermore, we conduct ablative experiments on the trainable components of the model to identify the crucial factors for effective transfer learning. Our findings demonstrate that unfreezing EVA-ViT-g to learn medical image representations, followed by parameter-efficient training of ChatGLM-6B to capture the writing styles of medical reports, is essential for achieving optimal results. Our best attempt (PCLmed Team) achieved the 4th and the 2nd, respectively, out of 13 participating teams, based on the BERTScore and ROUGE-1 metrics, in the ImageCLEFmedical Caption 2023 Caption Prediction Task competition.

Bang Yang, Fenglin Liu, Zheng Li et al.

Generating an informative and attractive title for the product is a crucial task for e-commerce. Most existing works follow the standard multimodal natural language generation approaches, e.g., image captioning, and employ the large scale of human-labelled datasets to train desirable models. However, for novel products, especially in a different domain, there are few existing labelled data. In this paper, we propose a prompt-based approach, i.e., the Multimodal Prompt Learning framework, to accurately and efficiently generate titles for novel products with limited labels. We observe that the core challenges of novel product title generation are the understanding of novel product characteristics and the generation of titles in a novel writing style. To this end, we build a set of multimodal prompts from different modalities to preserve the corresponding characteristics and writing styles of novel products. As a result, with extremely limited labels for training, the proposed method can retrieve the multimodal prompts to generate desirable titles for novel products. The experiments and analyses are conducted on five novel product categories under both the in-domain and out-of-domain experimental settings. The results show that, with only 1% of downstream labelled data for training, our proposed approach achieves the best few-shot results and even achieves competitive results with fully-supervised methods trained on 100% of training data; With the full labelled data for training, our method achieves state-of-the-art results.

Ji Jiang, Meng Cao, Tengtao Song et al.

Video Referring Expression Comprehension (REC) aims to localize a target object in videos based on the queried natural language. Recent improvements in video REC have been made using Transformer-based methods with learnable queries. However, we contend that this naive query design is not ideal given the open-world nature of video REC brought by text supervision. With numerous potential semantic categories, relying on only a few slow-updated queries is insufficient to characterize them. Our solution to this problem is to create dynamic queries that are conditioned on both the input video and language to model the diverse objects referred to. Specifically, we place a fixed number of learnable bounding boxes throughout the frame and use corresponding region features to provide prior information. Also, we noticed that current query features overlook the importance of cross-modal alignment. To address this, we align specific phrases in the sentence with semantically relevant visual areas, annotating them in existing video datasets (VID-Sentence and VidSTG). By incorporating these two designs, our proposed model (called ConFormer) outperforms other models on widely benchmarked datasets. For example, in the testing split of VID-Sentence dataset, ConFormer achieves 8.75% absolute improvement on Accu.@0.6 compared to the previous state-of-the-art model.

Chris Kelly, Luhui Hu, Cindy Yang et al.

In the current landscape of artificial intelligence, foundation models serve as the bedrock for advancements in both language and vision domains. OpenAI GPT-4 has emerged as the pinnacle in large language models (LLMs), while the computer vision (CV) domain boasts a plethora of state-of-the-art (SOTA) models such as Meta's SAM and DINO, and YOLOS. However, the financial and computational burdens of training new models from scratch remain a significant barrier to progress. In response to this challenge, we introduce UnifiedVisionGPT, a novel framework designed to consolidate and automate the integration of SOTA vision models, thereby facilitating the development of vision-oriented AI. UnifiedVisionGPT distinguishes itself through four key features: (1) provides a versatile multimodal framework adaptable to a wide range of applications, building upon the strengths of multimodal foundation models; (2) seamlessly integrates various SOTA vision models to create a comprehensive multimodal platform, capitalizing on the best components of each model; (3) prioritizes vision-oriented AI, ensuring a more rapid progression in the CV domain compared to the current trajectory of LLMs; and (4) introduces automation in the selection of SOTA vision models, generating optimal results based on diverse multimodal inputs such as text prompts and images. This paper outlines the architecture and capabilities of UnifiedVisionGPT, demonstrating its potential to revolutionize the field of computer vision through enhanced efficiency, versatility, generalization, and performance. Our implementation, along with the unified multimodal framework and comprehensive dataset, is made publicly available at https://github.com/LHBuilder/SA-Segment-Anything.

Tengtao Song, Nuo Chen, Ji Jiang et al.

Multi-turn response selection is a challenging task due to its high demands on efficient extraction of the matching features from abundant information provided by context utterances. Since incorporating syntactic information like dependency structures into neural models can promote a better understanding of the sentences, such a method has been widely used in NLP tasks. Though syntactic information helps models achieved pleasing results, its application in retrieval-based dialogue systems has not been fully explored. Meanwhile, previous works focus on intra-sentence syntax alone, which is far from satisfactory for the task of multi-turn response where dialogues usually contain multiple sentences. To this end, we propose SIA, Syntax-Informed Attention, considering both intra- and inter-sentence syntax information. While the former restricts attention scope to only between tokens and corresponding dependents in the syntax tree, the latter allows attention in cross-utterance pairs for those syntactically important tokens. We evaluate our method on three widely used benchmarks and experimental results demonstrate the general superiority of our method on dialogue response selection.

Ji Jiang, Meng Cao, Tengtao Song et al.

Video Referring Expression Comprehension (REC) aims to localize a target object in video frames referred by the natural language expression. Recently, the Transformerbased methods have greatly boosted the performance limit. However, we argue that the current query design is suboptima and suffers from two drawbacks: 1) the slow training convergence process; 2) the lack of fine-grained alignment. To alleviate this, we aim to couple the pure learnable queries with the content information. Specifically, we set up a fixed number of learnable bounding boxes across the frame and the aligned region features are employed to provide fruitful clues. Besides, we explicitly link certain phrases in the sentence to the semantically relevant visual areas. To this end, we introduce two new datasets (i.e., VID-Entity and VidSTG-Entity) by augmenting the VIDSentence and VidSTG datasets with the explicitly referred words in the whole sentence, respectively. Benefiting from this, we conduct the fine-grained cross-modal alignment at the region-phrase level, which ensures more detailed feature representations. Incorporating these two designs, our proposed model (dubbed as ContFormer) achieves the state-of-the-art performance on widely benchmarked datasets. For example on VID-Entity dataset, compared to the previous SOTA, ContFormer achieves 8.75% absolute improvement on Accu.@0.6.

Hao An, Dongsheng Chen, Weiyuan Xu et al.

Dialogue-based Relation Extraction (DRE) aims to predict the relation type of argument pairs that are mentioned in dialogue. The latest trigger-enhanced methods propose trigger prediction tasks to promote DRE. However, these methods are not able to fully leverage the trigger information and even bring noise to relation extraction. To solve these problems, we propose TLAG, which fully leverages the trigger and label-aware knowledge to guide the relation extraction. First, we design an adaptive trigger fusion module to fully leverage the trigger information. Then, we introduce label-aware knowledge to further promote our model's performance. Experimental results on the DialogRE dataset show that our TLAG outperforms the baseline models, and detailed analyses demonstrate the effectiveness of our approach.

Bang Yang, Yong Dai, Xuxin Cheng et al.

While vision-language pre-trained models (VL-PTMs) have advanced multimodal research in recent years, their mastery in a few languages like English restricts their applicability in broader communities. To this end, there is an increasing interest in developing multilingual VL models via a joint-learning setup, which, however, could be unrealistic due to expensive costs and data availability. In this work, we propose to extend VL-PTMs' language capacity by continual language learning (CLL), where a model needs to update its linguistic knowledge incrementally without suffering from catastrophic forgetting (CF). We begin our study by introducing a model dubbed CLL-CLIP, which builds upon CLIP, a prevailing VL-PTM that has acquired image-English text alignment. Specifically, CLL-CLIP contains an expandable token embedding layer to handle linguistic differences. It solely trains token embeddings to improve memory stability and is optimized under cross-modal and cross-lingual objectives to learn the alignment between images and multilingual texts. To alleviate CF raised by covariate shift and lexical overlap, we further propose a novel approach that ensures the identical distribution of all token embeddings during initialization and regularizes token embedding learning during training. We construct a CLL benchmark covering 36 languages based on MSCOCO and XM3600 datasets and then evaluate multilingual image-text retrieval performance. Extensive experiments verify the effectiveness of CLL-CLIP and show that our approach can boost CLL-CLIP, e.g., by 6.7% in text-to-image average Recall@1 on XM3600, and improve various state-of-the-art methods consistently. Our code and data are available at \url{https://github.com/yangbang18/CLFM}.

Yuguo Yin, Yuxin Xie, Wenyuan Yang et al.

Multilingual audio-text retrieval (ML-ATR) is a challenging task that aims to retrieve audio clips or multilingual texts from databases. However, existing ML-ATR schemes suffer from inconsistencies for instance similarity matching across languages. We theoretically analyze the inconsistency in terms of both multilingual modal alignment direction error and weight error, and propose the theoretical weight error upper bound for quantifying the inconsistency. Based on the analysis of the weight error upper bound, we find that the inconsistency problem stems from the data distribution error caused by random sampling of languages. We propose a consistent ML-ATR scheme using 1-to-k contrastive learning and audio-English co-anchor contrastive learning, aiming to mitigate the negative impact of data distribution error on recall and consistency in ML-ATR. Experimental results on the translated AudioCaps and Clotho datasets show that our scheme achieves state-of-the-art performance on recall and consistency metrics for eight mainstream languages, including English. Our code will be available at https://github.com/ATRI-ACL/ATRI-ACL.

Yaowei Li, Xiaoyu Li, Zhaoyang Zhang et al.

Image customization, a crucial technique for industrial media production, aims to generate content that is consistent with reference images. However, current approaches conventionally separate image customization into position-aware and position-free customization paradigms and lack a universal framework for diverse customization, limiting their applications across various scenarios. To overcome these limitations, we propose IC-Custom, a unified framework that seamlessly integrates position-aware and position-free image customization through in-context learning. IC-Custom concatenates reference images with target images to a polyptych, leveraging DiT's multi-modal attention mechanism for fine-grained token-level interactions. We propose the In-context Multi-Modal Attention (ICMA) mechanism, which employs learnable task-oriented register tokens and boundary-aware positional embeddings to enable the model to effectively handle diverse tasks and distinguish between inputs in polyptych configurations. To address the data gap, we curated a 12K identity-consistent dataset with 8K real-world and 4K high-quality synthetic samples, avoiding the overly glossy, oversaturated look typical of synthetic data. IC-Custom supports various industrial applications, including try-on, image insertion, and creative IP customization. Extensive evaluations on our proposed ProductBench and the publicly available DreamBench demonstrate that IC-Custom significantly outperforms community workflows, closed-source models, and state-of-the-art open-source approaches. IC-Custom achieves about 73\% higher human preference across identity consistency, harmony, and text alignment metrics, while training only 0.4\% of the original model parameters. Project page: https://liyaowei-stu.github.io/project/IC_Custom

Bowen Cao, Deng Cai, Zhisong Zhang et al.

The performance of large language models (LLMs) is acutely sensitive to the phrasing of prompts, which raises significant concerns about their reliability in real-world scenarios. Existing studies often divide prompts into task-level instructions and case-level inputs and primarily focus on evaluating and improving robustness against variations in tasks-level instructions. However, this setup fails to fully address the diversity of real-world user queries and assumes the existence of task-specific datasets. To address these limitations, we introduce RobustAlpacaEval, a new benchmark that consists of semantically equivalent case-level queries and emphasizes the importance of using the worst prompt performance to gauge the lower bound of model performance. Extensive experiments on RobustAlpacaEval with ChatGPT and six open-source LLMs from the Llama, Mistral, and Gemma families uncover substantial variability in model performance; for instance, a difference of 45.48% between the worst and best performance for the Llama-2-70B-chat model, with its worst performance dipping as low as 9.38%. We further illustrate the difficulty in identifying the worst prompt from both model-agnostic and model-dependent perspectives, emphasizing the absence of a shortcut to characterize the worst prompt. We also attempt to enhance the worst prompt performance using existing prompt engineering and prompt consistency methods, but find that their impact is limited. These findings underscore the need to create more resilient LLMs that can maintain high performance across diverse prompts. Data and code are available at https://github.com/cbwbuaa/On-the-Worst-Prompt- Performance-of-LLMs.

Chris Kelly, Luhui Hu, Bang Yang et al.

With the emergence of large language models (LLMs) and vision foundation models, how to combine the intelligence and capacity of these open-sourced or API-available models to achieve open-world visual perception remains an open question. In this paper, we introduce VisionGPT to consolidate and automate the integration of state-of-the-art foundation models, thereby facilitating vision-language understanding and the development of vision-oriented AI. VisionGPT builds upon a generalized multimodal framework that distinguishes itself through three key features: (1) utilizing LLMs (e.g., LLaMA-2) as the pivot to break down users' requests into detailed action proposals to call suitable foundation models; (2) integrating multi-source outputs from foundation models automatically and generating comprehensive responses for users; (3) adaptable to a wide range of applications such as text-conditioned image understanding/generation/editing and visual question answering. This paper outlines the architecture and capabilities of VisionGPT, demonstrating its potential to revolutionize the field of computer vision through enhanced efficiency, versatility, and generalization, and performance. Our code and models will be made publicly available. Keywords: VisionGPT, Open-world visual perception, Vision-language understanding, Large language model, and Foundation model

Zhongjie Ye, Helin Wang, Dongchao Yang et al.

Automated audio captioning (AAC) has developed rapidly in recent years, involving acoustic signal processing and natural language processing to generate human-readable sentences for audio clips. The current models are generally based on the neural encoder-decoder architecture, and their decoder mainly uses acoustic information that is extracted from the CNN-based encoder. However, they have ignored semantic information that could help the AAC model to generate meaningful descriptions. This paper proposes a novel approach for automated audio captioning based on incorporating semantic and acoustic information. Specifically, our audio captioning model consists of two sub-modules. (1) The pre-trained keyword encoder utilizes pre-trained ResNet38 to initialize its parameters, and then it is trained by extracted keywords as labels. (2) The multi-modal attention decoder adopts an LSTM-based decoder that contains semantic and acoustic attention modules. Experiments demonstrate that our proposed model achieves state-of-the-art performance on the Clotho dataset. Our code can be found at https://github.com/WangHelin1997/DCASE2021_Task6_PKU

Can Zhang, Meng Cao, Dongming Yang et al.

Weakly-supervised temporal action localization (WS-TAL) aims to localize actions in untrimmed videos with only video-level labels. Most existing models follow the "localization by classification" procedure: locate temporal regions contributing most to the video-level classification. Generally, they process each snippet (or frame) individually and thus overlook the fruitful temporal context relation. Here arises the single snippet cheating issue: "hard" snippets are too vague to be classified. In this paper, we argue that learning by comparing helps identify these hard snippets and we propose to utilize snippet Contrastive learning to Localize Actions, CoLA for short. Specifically, we propose a Snippet Contrast (SniCo) Loss to refine the hard snippet representation in feature space, which guides the network to perceive precise temporal boundaries and avoid the temporal interval interruption. Besides, since it is infeasible to access frame-level annotations, we introduce a Hard Snippet Mining algorithm to locate the potential hard snippets. Substantial analyses verify that this mining strategy efficaciously captures the hard snippets and SniCo Loss leads to more informative feature representation. Extensive experiments show that CoLA achieves state-of-the-art results on THUMOS'14 and ActivityNet v1.2 datasets. CoLA code is publicly available at https://github.com/zhang-can/CoLA.

Can Zhang, Yuexian Zou, Guang Chen et al.

Efficiently modeling dynamic motion information in videos is crucial for action recognition task. Most state-of-the-art methods heavily rely on dense optical flow as motion representation. Although combining optical flow with RGB frames as input can achieve excellent recognition performance, the optical flow extraction is very time-consuming. This undoubtably will count against real-time action recognition. In this paper, we shed light on fast action recognition by lifting the reliance on optical flow. Our motivation lies in the observation that small displacements of motion boundaries are the most critical ingredients for distinguishing actions, so we design a novel motion cue called Persistence of Appearance (PA). In contrast to optical flow, our PA focuses more on distilling the motion information at boundaries. Also, it is more efficient by only accumulating pixel-wise differences in feature space, instead of using exhaustive patch-wise search of all the possible motion vectors. Our PA is over 1000x faster (8196fps vs. 8fps) than conventional optical flow in terms of motion modeling speed. To further aggregate the short-term dynamics in PA to long-term dynamics, we also devise a global temporal fusion strategy called Various-timescale Aggregation Pooling (VAP) that can adaptively model long-range temporal relationships across various timescales. We finally incorporate the proposed PA and VAP to form a unified framework called Persistent Appearance Network (PAN) with strong temporal modeling ability. Extensive experiments on six challenging action recognition benchmarks verify that our PAN outperforms recent state-of-the-art methods at low FLOPs. Codes and models are available at: https://github.com/zhang-can/PAN-PyTorch.

Bang Yang, Yuexian Zou, Fenglin Liu et al.

It is encouraged to see that progress has been made to bridge videos and natural language. However, mainstream video captioning methods suffer from slow inference speed due to the sequential manner of autoregressive decoding, and prefer generating generic descriptions due to the insufficient training of visual words (e.g., nouns and verbs) and inadequate decoding paradigm. In this paper, we propose a non-autoregressive decoding based model with a coarse-to-fine captioning procedure to alleviate these defects. In implementations, we employ a bi-directional self-attention based network as our language model for achieving inference speedup, based on which we decompose the captioning procedure into two stages, where the model has different focuses. Specifically, given that visual words determine the semantic correctness of captions, we design a mechanism of generating visual words to not only promote the training of scene-related words but also capture relevant details from videos to construct a coarse-grained sentence "template". Thereafter, we devise dedicated decoding algorithms that fill in the "template" with suitable words and modify inappropriate phrasing via iterative refinement to obtain a fine-grained description. Extensive experiments on two mainstream video captioning benchmarks, i.e., MSVD and MSR-VTT, demonstrate that our approach achieves state-of-the-art performance, generates diverse descriptions, and obtains high inference efficiency. Our code is available at https://github.com/yangbang18/Non-Autoregressive-Video-Captioning.

Deshun Yang, Luhui Hu, Yu Tian et al.

Several text-to-video diffusion models have demonstrated commendable capabilities in synthesizing high-quality video content. However, it remains a formidable challenge pertaining to maintaining temporal consistency and ensuring action smoothness throughout the generated sequences. In this paper, we present an innovative video generation AI agent that harnesses the power of Sora-inspired multimodal learning to build skilled world models framework based on textual prompts and accompanying images. The framework includes two parts: prompt enhancer and full video translation. The first part employs the capabilities of ChatGPT to meticulously distill and proactively construct precise prompts for each subsequent step, thereby guaranteeing the utmost accuracy in prompt communication and accurate execution in following model operations. The second part employ compatible with existing advanced diffusion techniques to expansively generate and refine the key frame at the conclusion of a video. Then we can expertly harness the power of leading and trailing key frames to craft videos with enhanced temporal consistency and action smoothness. The experimental results confirm that our method has strong effectiveness and novelty in constructing world models from text and image inputs over the other methods.

Bowen Cao, Deng Cai, Leyang Cui et al.

Standard language models generate text by selecting tokens from a fixed, finite, and standalone vocabulary. We introduce a novel method that selects context-aware phrases from a collection of supporting documents. One of the most significant challenges for this paradigm shift is determining the training oracles, because a string of text can be segmented in various ways and each segment can be retrieved from numerous possible documents. To address this, we propose to initialize the training oracles using linguistic heuristics and, more importantly, bootstrap the oracles through iterative self-reinforcement. Extensive experiments show that our model not only outperforms standard language models on a variety of knowledge-intensive tasks but also demonstrates improved generation quality in open-ended text generation. For instance, compared to the standard language model counterpart, our model raises the accuracy from 23.47% to 36.27% on OpenbookQA, and improves the MAUVE score from 42.61% to 81.58% in open-ended text generation. Remarkably, our model also achieves the best performance and the lowest latency among several retrieval-augmented baselines. In conclusion, we assert that retrieval is more accurate generation and hope that our work will encourage further research on this new paradigm shift.

Yaowei Li, Lingen Li, Zhaoyang Zhang et al.

As user expectations for image editing continue to rise, the demand for flexible, fine-grained manipulation of specific visual elements presents a challenge for current diffusion-based methods. In this work, we present BlobCtrl, a framework for element-level image editing based on a probabilistic blob-based representation. Treating blobs as visual primitives, BlobCtrl disentangles layout from appearance, affording fine-grained, controllable object-level manipulation. Our key contributions are twofold: (1) an in-context dual-branch diffusion model that separates foreground and background processing, incorporating blob representations to explicitly decouple layout and appearance, and (2) a self-supervised disentangle-then-reconstruct training paradigm with an identity-preserving loss function, along with tailored strategies to efficiently leverage blob-image pairs. To foster further research, we introduce BlobData for large-scale training and BlobBench, a benchmark for systematic evaluation. Experimental results demonstrate that BlobCtrl achieves state-of-the-art performance in a variety of element-level editing tasks, such as object addition, removal, scaling, and replacement, while maintaining computational efficiency. Project Webpage: https://liyaowei-stu.github.io/project/BlobCtrl/

Xusheng Yang, Long Zhou, Wenfu Wang et al.

We propose \textbf{U-Codec}, an \textbf{U}ltra low frame-rate neural speech \textbf{Codec} that achieves high-fidelity reconstruction and fast speech generation at an extremely low frame-rate of 5Hz (5 frames per second). Extreme compression at 5Hz typically leads to severe intelligibility and spectral detail loss, we introduce a Transformer-based inter-frame long-term dependency module and systematically explore residual vector quantization (RVQ) depth and codebook size to identify optimal configurations. Moreover, we apply U-Codec into a large language model (LLM)-based auto-regressive TTS model, which leverages global and local hierarchical architecture to effectively capture dependencies across multi-layer tokens. We extend LLM-based TTS from 3-layer RVQ at 50Hz to 32-layer RVQ at 5Hz. Experimental results demonstrate that U-Codec improves LLM-based TTS inference speed by around 3 $\times$ over high-frame-rate codecs while maintaining similarity and naturalness. These results validate the feasibility of using highly compressed 5Hz discrete tokens for fast and high-fidelity speech synthesis.

Lexiang Tang, Xianwei Zhuang, Bang Yang et al.

Large vision-language models (LVLMs) have demonstrated impressive capabilities across diverse multimodal tasks, yet they remain highly susceptible to visual hallucinations (VH), often producing confident but inaccurate descriptions of visual content. Building on the insight that not all tokens and attention heads contribute equally to VH mitigation, we introduce VisFlow, a lightweight and training-free framework that alleviates hallucinations by directly modulating attention patterns during inference. To address two primary challenges of VH, namely insufficient visual attention and the dominance of language priors, we identify three problematic attention behaviors in LVLMs: (1) disproportionate allocation of attention to uninformative or trailing visual tokens, (2) over-dependence on the previously generated token, and (3) excessive fixation on system prompts that hinders multimodal integration. To overcome these issues, VisFlow introduces a dual-level Attention Intervention, consisting of Token-level Attention Intervention (TAI), which reinforces attention to salient visual regions, and Head-level Attention Intervention (HAI), which suppresses undue focus on system prompts and adjacent text tokens. Together, these interventions strengthen visual alignment while reducing linguistic bias. Extensive experiments across diverse models and benchmarks demonstrate that VisFlow effectively mitigates hallucinations with minimal computational overhead.

Yaowei Li, Xintao Wang, Zhaoyang Zhang et al.

Filmmaking and animation production often require sophisticated techniques for coordinating camera transitions and object movements, typically involving labor-intensive real-world capturing. Despite advancements in generative AI for video creation, achieving precise control over motion for interactive video asset generation remains challenging. To this end, we propose Image Conductor, a method for precise control of camera transitions and object movements to generate video assets from a single image. An well-cultivated training strategy is proposed to separate distinct camera and object motion by camera LoRA weights and object LoRA weights. To further address cinematographic variations from ill-posed trajectories, we introduce a camera-free guidance technique during inference, enhancing object movements while eliminating camera transitions. Additionally, we develop a trajectory-oriented video motion data curation pipeline for training. Quantitative and qualitative experiments demonstrate our method's precision and fine-grained control in generating motion-controllable videos from images, advancing the practical application of interactive video synthesis. Project webpage available at https://liyaowei-stu.github.io/project/ImageConductor/

Chris Kelly, Luhui Hu, Jiayin Hu et al.

The evolution of text to visual components facilitates people's daily lives, such as generating image, videos from text and identifying the desired elements within the images. Computer vision models involving the multimodal abilities in the previous days are focused on image detection, classification based on well-defined objects. Large language models (LLMs) introduces the transformation from nature language to visual objects, which present the visual layout for text contexts. OpenAI GPT-4 has emerged as the pinnacle in LLMs, while the computer vision (CV) domain boasts a plethora of state-of-the-art (SOTA) models and algorithms to convert 2D images to their 3D representations. However, the mismatching between the algorithms with the problem could lead to undesired results. In response to this challenge, we propose an unified VisionGPT-3D framework to consolidate the state-of-the-art vision models, thereby facilitating the development of vision-oriented AI. VisionGPT-3D provides a versatile multimodal framework building upon the strengths of multimodal foundation models. It seamlessly integrates various SOTA vision models and brings the automation in the selection of SOTA vision models, identifies the suitable 3D mesh creation algorithms corresponding to 2D depth maps analysis, generates optimal results based on diverse multimodal inputs such as text prompts. Keywords: VisionGPT-3D, 3D vision understanding, Multimodal agent

Li Wang, Rongzhi Gu, Weiji Zhuang et al.

Keyword spotting (KWS) and speaker verification (SV) are two important tasks in speech applications. Research shows that the state-of-art KWS and SV models are trained independently using different datasets since they expect to learn distinctive acoustic features. However, humans can distinguish language content and the speaker identity simultaneously. Motivated by this, we believe it is important to explore a method that can effectively extract common features while decoupling task-specific features. Bearing this in mind, a two-branch deep network (KWS branch and SV branch) with the same network structure is developed and a novel decoupling feature learning method is proposed to push up the performance of KWS and SV simultaneously where speaker-invariant keyword representations and keyword-invariant speaker representations are expected respectively. Experiments are conducted on Google Speech Commands Dataset (GSCD). The results demonstrate that the orthogonality regularization helps the network to achieve SOTA EER of 1.31% and 1.87% on KWS and SV, respectively.

Liyu Wu, Can Zhang, Yuexian Zou

Graph convolutional networks (GCNs) are widely adopted in skeleton-based action recognition due to their powerful ability to model data topology. We argue that the performance of recent proposed skeleton-based action recognition methods is limited by the following factors. First, the predefined graph structures are shared throughout the network, lacking the flexibility and capacity to model the multi-grain semantic information. Second, the relations among the global joints are not fully exploited by the graph local convolution, which may lose the implicit joint relevance. For instance, actions such as running and waving are performed by the co-movement of body parts and joints, e.g., legs and arms, however, they are located far away in physical connection. Inspired by the recent attention mechanism, we propose a multi-grain contextual focus module, termed MCF, to capture the action associated relation information from the body joints and parts. As a result, more explainable representations for different skeleton action sequences can be obtained by MCF. In this study, we follow the common practice that the dense sample strategy of the input skeleton sequences is adopted and this brings much redundancy since number of instances has nothing to do with actions. To reduce the redundancy, a temporal discrimination focus module, termed TDF, is developed to capture the local sensitive points of the temporal dynamics. MCF and TDF are integrated into the standard GCN network to form a unified architecture, named STF-Net. It is noted that STF-Net provides the capability to capture robust movement patterns from these skeleton topology structures, based on multi-grain context aggregation and temporal dependency. Extensive experimental results show that our STF-Net significantly achieves state-of-the-art results on three challenging benchmarks NTU RGB+D 60, NTU RGB+D 120, and Kinetics-skeleton.

Jinchuan Tian, Jianwei Yu, Chao Weng et al.

Despite the rapid progress of end-to-end (E2E) automatic speech recognition (ASR), it has been shown that incorporating external language models (LMs) into the decoding can further improve the recognition performance of E2E ASR systems. To align with the modeling units adopted in E2E ASR systems, subword-level (e.g., characters, BPE) LMs are usually used to cooperate with current E2E ASR systems. However, the use of subword-level LMs will ignore the word-level information, which may limit the strength of the external LMs in E2E ASR. Although several methods have been proposed to incorporate word-level external LMs in E2E ASR, these methods are mainly designed for languages with clear word boundaries such as English and cannot be directly applied to languages like Mandarin, in which each character sequence can have multiple corresponding word sequences. To this end, we propose a novel decoding algorithm where a word-level lattice is constructed on-the-fly to consider all possible word sequences for each partial hypothesis. Then, the LM score of the hypothesis is obtained by intersecting the generated lattice with an external word N-gram LM. The proposed method is examined on both Attention-based Encoder-Decoder (AED) and Neural Transducer (NT) frameworks. Experiments suggest that our method consistently outperforms subword-level LMs, including N-gram LM and neural network LM. We achieve state-of-the-art results on both Aishell-1 (CER 4.18%) and Aishell-2 (CER 5.06%) datasets and reduce CER by 14.8% relatively on a 21K-hour Mandarin dataset.

Dongchao Yang, Helin Wang, Yuexian Zou et al.

Human beings can perceive a target sound type from a multi-source mixture signal by the selective auditory attention, however, such functionality was hardly ever explored in machine hearing. This paper addresses the target sound detection (TSD) task, which aims to detect the target sound signal from a mixture audio when a target sound's reference audio is given. We present a novel target sound detection network (TSDNet) which consists of two main parts: A conditional network which aims at generating a sound-discriminative conditional embedding vector representing the target sound, and a detection network which takes both the mixture audio and the conditional embedding vector as inputs and produces the detection result of the target sound. These two networks can be jointly optimized with a multi-task learning approach to further improve the performance. In addition, we study both strong-supervised and weakly-supervised strategies to train TSDNet and propose a data augmentation method by mixing two samples. To facilitate this research, we build a target sound detection dataset (\textit{i.e.} URBAN-TSD) based on URBAN-SED and UrbanSound8K datasets, and experimental results indicate our method could get the segment-based F scores of 76.3$\%$ and 56.8$\%$ on the strongly-labelled and weakly-labelled data respectively.