Yu Zhou

Bo Fang, Wenhao Wu, Chang Liu et al. · amazon-science

With the explosive growth of web videos and emerging large-scale vision-language pre-training models, e.g., CLIP, retrieving videos of interest with text instructions has attracted increasing attention. A common practice is to transfer text-video pairs to the same embedding space and craft cross-modal interactions with certain entities in specific granularities for semantic correspondence. Unfortunately, the intrinsic uncertainties of optimal entity combinations in appropriate granularities for cross-modal queries are understudied, which is especially critical for modalities with hierarchical semantics, e.g., video, text, etc. In this paper, we propose an Uncertainty-Adaptive Text-Video Retrieval approach, termed UATVR, which models each look-up as a distribution matching procedure. Concretely, we add additional learnable tokens in the encoders to adaptively aggregate multi-grained semantics for flexible high-level reasoning. In the refined embedding space, we represent text-video pairs as probabilistic distributions where prototypes are sampled for matching evaluation. Comprehensive experiments on four benchmarks justify the superiority of our UATVR, which achieves new state-of-the-art results on MSR-VTT (50.8%), VATEX (64.5%), MSVD (49.7%), and DiDeMo (45.8%). The code is available at https://github.com/bofang98/UATVR.

Zhou Yu, Xuecheng Ouyang, Zhenwei Shao et al.

Knowledge-based visual question answering (VQA) requires external knowledge beyond the image to answer the question. Early studies retrieve required knowledge from explicit knowledge bases (KBs), which often introduces irrelevant information to the question, hence restricting the performance of their models. Recent works have resorted to using a powerful large language model (LLM) as an implicit knowledge engine to acquire the necessary knowledge for answering. Despite the encouraging results achieved by these methods, we argue that they have not fully activated the capacity of the \emph{blind} LLM as the provided textual input is insufficient to depict the required visual information to answer the question. In this paper, we present Prophet -- a conceptually simple, flexible, and general framework designed to prompt LLM with answer heuristics for knowledge-based VQA. Specifically, we first train a vanilla VQA model on a specific knowledge-based VQA dataset without external knowledge. After that, we extract two types of complementary answer heuristics from the VQA model: answer candidates and answer-aware examples. The two types of answer heuristics are jointly encoded into a formatted prompt to facilitate the LLM's understanding of both the image and question, thus generating a more accurate answer. By incorporating the state-of-the-art LLM GPT-3, Prophet significantly outperforms existing state-of-the-art methods on four challenging knowledge-based VQA datasets. Prophet is general that can be instantiated with the combinations of different VQA models (i.e., both discriminative and generative ones) and different LLMs (i.e., both commercial and open-source ones). Moreover, Prophet can also be integrated with modern large multimodal models in different stages, which is named Prophet++, to further improve the capabilities on knowledge-based VQA tasks.

Mingyang Zhou, Licheng Yu, Amanpreet Singh et al. · meta-ai

Vision-and-Language (V+L) pre-training models have achieved tremendous success in recent years on various multi-modal benchmarks. However, the majority of existing models require pre-training on a large set of parallel image-text data, which is costly to collect, compared to image-only or text-only data. In this paper, we explore unsupervised Vision-and-Language pre-training (UVLP) to learn the cross-modal representation from non-parallel image and text datasets. We found two key factors that lead to good unsupervised V+L pre-training without parallel data: (i) joint image-and-text input (ii) overall image-text alignment (even for non-parallel data). Accordingly, we propose a novel unsupervised V+L pre-training curriculum for non-parallel texts and images. We first construct a weakly aligned image-text corpus via a retrieval-based approach, then apply a set of multi-granular alignment pre-training tasks, including region-to-tag, region-to-phrase, and image-to-sentence alignment, to bridge the gap between the two modalities. A comprehensive ablation study shows each granularity is helpful to learn a stronger pre-trained model. We adapt our pre-trained model to a set of V+L downstream tasks, including VQA, NLVR2, Visual Entailment, and RefCOCO+. Our model achieves the state-of-art performance in all these tasks under the unsupervised setting.

Gangyan Zeng, Yuan Zhang, Jin Wei et al.

Scene text retrieval aims to find all images containing the query text from an image gallery. Current efforts tend to adopt an Optical Character Recognition (OCR) pipeline, which requires complicated text detection and/or recognition processes, resulting in inefficient and inflexible retrieval. Different from them, in this work we propose to explore the intrinsic potential of Contrastive Language-Image Pre-training (CLIP) for OCR-free scene text retrieval. Through empirical analysis, we observe that the main challenges of CLIP as a text retriever are: 1) limited text perceptual scale, and 2) entangled visual-semantic concepts. To this end, a novel model termed FDP (Focus, Distinguish, and Prompt) is developed. FDP first focuses on scene text via shifting the attention to the text area and probing the hidden text knowledge, and then divides the query text into content word and function word for processing, in which a semantic-aware prompting scheme and a distracted queries assistance module are utilized. Extensive experiments show that FDP significantly enhances the inference speed while achieving better or competitive retrieval accuracy compared to existing methods. Notably, on the IIIT-STR benchmark, FDP surpasses the state-of-the-art model by 4.37% with a 4 times faster speed. Furthermore, additional experiments under phrase-level and attribute-aware scene text retrieval settings validate FDP's particular advantages in handling diverse forms of query text. The source code will be publicly available at https://github.com/Gyann-z/FDP.

Mengfei Xia, Yujun Shen, Changsong Lei et al.

A diffusion model, which is formulated to produce an image using thousands of denoising steps, usually suffers from a slow inference speed. Existing acceleration algorithms simplify the sampling by skipping most steps yet exhibit considerable performance degradation. By viewing the generation of diffusion models as a discretized integral process, we argue that the quality drop is partly caused by applying an inaccurate integral direction to a timestep interval. To rectify this issue, we propose a \textbf{timestep tuner} that helps find a more accurate integral direction for a particular interval at the minimum cost. Specifically, at each denoising step, we replace the original parameterization by conditioning the network on a new timestep, enforcing the sampling distribution towards the real one. Extensive experiments show that our plug-in design can be trained efficiently and boost the inference performance of various state-of-the-art acceleration methods, especially when there are few denoising steps. For example, when using 10 denoising steps on LSUN Bedroom dataset, we improve the FID of DDIM from 9.65 to 6.07, simply by adopting our method for a more appropriate set of timesteps. Code is available at \href{https://github.com/THU-LYJ-Lab/time-tuner}{https://github.com/THU-LYJ-Lab/time-tuner}.

Mingyang Zhou, Grace Luo, Anna Rohrbach et al.

News Image Captioning requires describing an image by leveraging additional context from a news article. Previous works only coarsely leverage the article to extract the necessary context, which makes it challenging for models to identify relevant events and named entities. In our paper, we first demonstrate that by combining more fine-grained context that captures the key named entities (obtained via an oracle) and the global context that summarizes the news, we can dramatically improve the model's ability to generate accurate news captions. This begs the question, how to automatically extract such key entities from an image? We propose to use the pre-trained vision and language retrieval model CLIP to localize the visually grounded entities in the news article and then capture the non-visual entities via an open relation extraction model. Our experiments demonstrate that by simply selecting a better context from the article, we can significantly improve the performance of existing models and achieve new state-of-the-art performance on multiple benchmarks.

Yang Zhao, Junnan Zhu, Lu Xiang et al.

A common scenario of Multilingual Neural Machine Translation (MNMT) is that each translation task arrives in a sequential manner, and the training data of previous tasks is unavailable. In this scenario, the current methods suffer heavily from catastrophic forgetting (CF). To alleviate the CF, we investigate knowledge distillation based life-long learning methods. Specifically, in one-tomany scenario, we propose a multilingual distillation method to make the new model (student) jointly learn multilingual output from old model (teacher) and new task. In many-to one scenario, we find that direct distillation faces the extreme partial distillation problem, and we propose two different methods to address it: pseudo input distillation and reverse teacher distillation. The experimental results on twelve translation tasks show that the proposed methods can better consolidate the previous knowledge and sharply alleviate the CF.

Zhou Yu, Zitian Jin, Jun Yu et al.

Recent advances in Transformer architectures [1] have brought remarkable improvements to visual question answering (VQA). Nevertheless, Transformer-based VQA models are usually deep and wide to guarantee good performance, so they can only run on powerful GPU servers and cannot run on capacity-restricted platforms such as mobile phones. Therefore, it is desirable to learn an elastic VQA model that supports adaptive pruning at runtime to meet the efficiency constraints of different platforms. To this end, we present the bilaterally slimmable Transformer (BST), a general framework that can be seamlessly integrated into arbitrary Transformer-based VQA models to train a single model once and obtain various slimmed submodels of different widths and depths. To verify the effectiveness and generality of this method, we integrate the proposed BST framework with three typical Transformer-based VQA approaches, namely MCAN [2], UNITER [3], and CLIP-ViL [4], and conduct extensive experiments on two commonly-used benchmark datasets. In particular, one slimmed MCAN-BST submodel achieves comparable accuracy on VQA-v2, while being 0.38x smaller in model size and having 0.27x fewer FLOPs than the reference MCAN model. The smallest MCAN-BST submodel only has 9M parameters and 0.16G FLOPs during inference, making it possible to deploy it on a mobile device with less than 60 ms latency.

Cong Ma, Yaping Zhang, Mei Tu et al.

End-to-end text image translation (TIT), which aims at translating the source language embedded in images to the target language, has attracted intensive attention in recent research. However, data sparsity limits the performance of end-to-end text image translation. Multi-task learning is a non-trivial way to alleviate this problem via exploring knowledge from complementary related tasks. In this paper, we propose a novel text translation enhanced text image translation, which trains the end-to-end model with text translation as an auxiliary task. By sharing model parameters and multi-task training, our model is able to take full advantage of easily-available large-scale text parallel corpus. Extensive experimental results show our proposed method outperforms existing end-to-end methods, and the joint multi-task learning with both text translation and recognition tasks achieves better results, proving translation and recognition auxiliary tasks are complementary.

Youhui Guo, Yu Zhou, Xugong Qin et al.

Recent scene text detection methods are almost based on deep learning and data-driven. Synthetic data is commonly adopted for pre-training due to expensive annotation cost. However, there are obvious domain discrepancies between synthetic data and real-world data. It may lead to sub-optimal performance to directly adopt the model initialized by synthetic data in the fine-tuning stage. In this paper, we propose a new training paradigm for scene text detection, which introduces an \textbf{UN}supervised \textbf{I}ntermediate \textbf{T}raining \textbf{S}tage (UNITS) that builds a buffer path to real-world data and can alleviate the gap between the pre-training stage and fine-tuning stage. Three training strategies are further explored to perceive information from real-world data in an unsupervised way. With UNITS, scene text detectors are improved without introducing any parameters and computations during inference. Extensive experimental results show consistent performance improvements on three public datasets.

Chengyang Fang, Gangyan Zeng, Yu Zhou et al.

Texts in scene images convey critical information for scene understanding and reasoning. The abilities of reading and reasoning matter for the model in the text-based visual question answering (TextVQA) process. However, current TextVQA models do not center on the text and suffer from several limitations. The model is easily dominated by language biases and optical character recognition (OCR) errors due to the absence of semantic guidance in the answer prediction process. In this paper, we propose a novel Semantics-Centered Network (SC-Net) that consists of an instance-level contrastive semantic prediction module (ICSP) and a semantics-centered transformer module (SCT). Equipped with the two modules, the semantics-centered model can resist the language biases and the accumulated errors from OCR. Extensive experiments on TextVQA and ST-VQA datasets show the effectiveness of our model. SC-Net surpasses previous works with a noticeable margin and is more reasonable for the TextVQA task.

Sky CH-Wang, Evan Li, Oliver Li et al.

Affective responses to music are highly personal. Despite consensus that idiosyncratic factors play a key role in regulating how listeners emotionally respond to music, precisely measuring the marginal effects of these variables has proved challenging. To address this gap, we develop computational methods to measure affective responses to music from over 403M listener comments on a Chinese social music platform. Building on studies from music psychology in systematic and quasi-causal analyses, we test for musical, lyrical, contextual, demographic, and mental health effects that drive listener affective responses. Finally, motivated by the social phenomenon known as wǎng-yì-yún, we identify influencing factors of platform user self-disclosures, the social support they receive, and notable differences in discloser user activity.

Yu Zhou, Liyuan Guo, Lianghai Jin

Facial expression recognition (FER) is a challenging topic in artificial intelligence. Recently, many researchers have attempted to introduce Vision Transformer (ViT) to the FER task. However, ViT cannot fully utilize emotional features extracted from raw images and requires a lot of computing resources. To overcome these problems, we propose a quaternion orthogonal transformer (QOT) for FER. Firstly, to reduce redundancy among features extracted from pre-trained ResNet-50, we use the orthogonal loss to decompose and compact these features into three sets of orthogonal sub-features. Secondly, three orthogonal sub-features are integrated into a quaternion matrix, which maintains the correlations between different orthogonal components. Finally, we develop a quaternion vision transformer (Q-ViT) for feature classification. The Q-ViT adopts quaternion operations instead of the original operations in ViT, which improves the final accuracies with fewer parameters. Experimental results on three in-the-wild FER datasets show that the proposed QOT outperforms several state-of-the-art models and reduces the computations.

Jinhui Lou, Yan Yang, Zhou Yu et al.

Chest X-ray (CXR) plays a pivotal role in clinical diagnosis, and a variety of task-specific and foundation models have been developed for automatic CXR interpretation. However, these models often struggle to adapt to new diagnostic tasks and complex reasoning scenarios. Recently, LLM-based agent models have emerged as a promising paradigm for CXR analysis, enhancing model's capability through tool coordination, multi-step reasoning, and team collaboration, etc. However, existing agents often rely on a single diagnostic pipeline and lack mechanisms for assessing tools' reliability, limiting their adaptability and credibility. To this end, we propose CXRAgent, a director-orchestrated, multi-stage agent for CXR interpretation, where a central director coordinates the following stages: (1) Tool Invocation: The agent strategically orchestrates a set of CXR-analysis tools, with outputs normalized and verified by the Evidence-driven Validator (EDV), which grounds diagnostic outputs with visual evidence to support reliable downstream diagnosis; (2) Diagnostic Planning: Guided by task requirements and intermediate findings, the agent formulates a targeted diagnostic plan. It then assembles an expert team accordingly, defining member roles and coordinating their interactions to enable adaptive and collaborative reasoning; (3) Collaborative Decision-making: The agent integrates insights from the expert team with accumulated contextual memories, synthesizing them into an evidence-backed diagnostic conclusion. Experiments on various CXR interpretation tasks show that CXRAgent delivers strong performance, providing visual evidence and generalizes well to clinical tasks of different complexity. Code and data are valuable at this \href{https://github.com/laojiahuo2003/CXRAgent/}{link}.

Zhuokang Shen, Kaisen Zhang, Bohan Jia et al.

With the increasing prevalence of synthetic images, evaluating image authenticity and locating forgeries accurately while maintaining human interpretability remains a challenging task. Existing detection models primarily focus on simple authenticity classification, ultimately providing only a forgery probability or binary judgment, which offers limited explanatory insights into image authenticity. Moreover, while MLLM-based detection methods can provide more interpretable results, they still lag behind expert models in terms of pure authenticity classification accuracy. To address this, we propose DF-LLaVA, a simple yet effective framework that unlocks the intrinsic discrimination potential of MLLMs. Our approach first extracts latent knowledge from MLLMs and then injects it into training via prompts. This framework allows LLaVA to achieve outstanding detection accuracy exceeding expert models while still maintaining the interpretability offered by MLLMs. Extensive experiments confirm the superiority of our DF-LLaVA, achieving both high accuracy and explainability in synthetic image detection. Code is available online at: https://github.com/Eliot-Shen/DF-LLaVA.

Xuechen Liang, Xiaoxing He, Shengdao Wang et al.

Geodetic time series -- such as Global Navigation Satellite System (GNSS) positions, satellite altimetry-derived sea surface height (SSH), and tide gauge (TG) records -- is essential for monitoring surface deformation and sea level change. Accurate forecasts of these variables can enhance early warning systems and support hazard mitigation for earthquakes, landslides, coastal storm surge, and long-term sea level. However, the nonlinear, non-stationary, and incomplete nature of such variables presents significant challenges for classic models, which often fail to capture long-term dependencies and complex spatiotemporal dynamics. We introduce GTS Forecaster, an open-source Python package for geodetic time series forecasting. It integrates advanced deep learning models -- including kernel attention networks (KAN), graph neural network-based gated recurrent units (GNNGRU), and time-aware graph neural networks (TimeGNN) -- to effectively model nonlinear spatial-temporal patterns. The package also provides robust preprocessing tools, including outlier detection and a reinforcement learning-based gap-filling algorithm, the Kalman-TransFusion Interpolation Framework (KTIF). GTS Forecaster currently supports forecasting, visualization, and evaluation of GNSS, SSH, and TG datasets, and is adaptable to general time series applications. By combining cutting-edge models with an accessible interface, it facilitates the application of deep learning in geodetic forecasting tasks.

Zhou Yu, Jun Yu, Yuhao Cui et al.

Visual Question Answering (VQA) requires a fine-grained and simultaneous understanding of both the visual content of images and the textual content of questions. Therefore, designing an effective `co-attention' model to associate key words in questions with key objects in images is central to VQA performance. So far, most successful attempts at co-attention learning have been achieved by using shallow models, and deep co-attention models show little improvement over their shallow counterparts. In this paper, we propose a deep Modular Co-Attention Network (MCAN) that consists of Modular Co-Attention (MCA) layers cascaded in depth. Each MCA layer models the self-attention of questions and images, as well as the guided-attention of images jointly using a modular composition of two basic attention units. We quantitatively and qualitatively evaluate MCAN on the benchmark VQA-v2 dataset and conduct extensive ablation studies to explore the reasons behind MCAN's effectiveness. Experimental results demonstrate that MCAN significantly outperforms the previous state-of-the-art. Our best single model delivers 70.63$\%$ overall accuracy on the test-dev set. Code is available at https://github.com/MILVLG/mcan-vqa.

Zhou Yu, Dejing Xu, Jun Yu et al.

Recent developments in modeling language and vision have been successfully applied to image question answering. It is both crucial and natural to extend this research direction to the video domain for video question answering (VideoQA). Compared to the image domain where large scale and fully annotated benchmark datasets exists, VideoQA datasets are limited to small scale and are automatically generated, etc. These limitations restrict their applicability in practice. Here we introduce ActivityNet-QA, a fully annotated and large scale VideoQA dataset. The dataset consists of 58,000 QA pairs on 5,800 complex web videos derived from the popular ActivityNet dataset. We present a statistical analysis of our ActivityNet-QA dataset and conduct extensive experiments on it by comparing existing VideoQA baselines. Moreover, we explore various video representation strategies to improve VideoQA performance, especially for long videos. The dataset is available at https://github.com/MILVLG/activitynet-qa

Zhou Yu, Jun Yu, Jianping Fan et al.

Visual question answering (VQA) is challenging because it requires a simultaneous understanding of both the visual content of images and the textual content of questions. The approaches used to represent the images and questions in a fine-grained manner and questions and to fuse these multi-modal features play key roles in performance. Bilinear pooling based models have been shown to outperform traditional linear models for VQA, but their high-dimensional representations and high computational complexity may seriously limit their applicability in practice. For multi-modal feature fusion, here we develop a Multi-modal Factorized Bilinear (MFB) pooling approach to efficiently and effectively combine multi-modal features, which results in superior performance for VQA compared with other bilinear pooling approaches. For fine-grained image and question representation, we develop a co-attention mechanism using an end-to-end deep network architecture to jointly learn both the image and question attentions. Combining the proposed MFB approach with co-attention learning in a new network architecture provides a unified model for VQA. Our experimental results demonstrate that the single MFB with co-attention model achieves new state-of-the-art performance on the real-world VQA dataset. Code available at https://github.com/yuzcccc/mfb.

Yu Zhou, Xingyu Wu, Beicheng Huang et al.

The ability to understand causality significantly impacts the competence of large language models (LLMs) in output explanation and counterfactual reasoning, as causality reveals the underlying data distribution. However, the lack of a comprehensive benchmark currently limits the evaluation of LLMs' causal learning capabilities. To fill this gap, this paper develops CausalBench based on data from the causal research community, enabling comparative evaluations of LLMs against traditional causal learning algorithms. To provide a comprehensive investigation, we offer three tasks of varying difficulties, including correlation, causal skeleton, and causality identification. Evaluations of 19 leading LLMs reveal that, while closed-source LLMs show potential for simple causal relationships, they significantly lag behind traditional algorithms on larger-scale networks ($>50$ nodes). Specifically, LLMs struggle with collider structures but excel at chain structures, especially at long-chain causality analogous to Chains-of-Thought techniques. This supports the current prompt approaches while suggesting directions to enhance LLMs' causal reasoning capability. Furthermore, CausalBench incorporates background knowledge and training data into prompts to thoroughly unlock LLMs' text-comprehension ability during evaluation, whose findings indicate that, LLM understand causality through semantic associations with distinct entities, rather than directly from contextual information or numerical distributions.

Xiaomeng Yang, Zhi Qiao, Yu Zhou

Nowadays, scene text recognition has attracted more and more attention due to its diverse applications. Most state-of-the-art methods adopt an encoder-decoder framework with the attention mechanism, autoregressively generating text from left to right. Despite the convincing performance, this sequential decoding strategy constrains the inference speed. Conversely, non-autoregressive models provide faster, simultaneous predictions but often sacrifice accuracy. Although utilizing an explicit language model can improve performance, it burdens the computational load. Besides, separating linguistic knowledge from vision information may harm the final prediction. In this paper, we propose an alternative solution that uses a parallel and iterative decoder that adopts an easy-first decoding strategy. Furthermore, we regard text recognition as an image-based conditional text generation task and utilize the discrete diffusion strategy, ensuring exhaustive exploration of bidirectional contextual information. Extensive experiments demonstrate that the proposed approach achieves superior results on the benchmark datasets, including both Chinese and English text images.

Jiahao Lyu, Jin Wei, Gangyan Zeng et al.

Existing scene text spotters are designed to locate and transcribe texts from images. However, it is challenging for a spotter to achieve precise detection and recognition of scene texts simultaneously. Inspired by the glimpse-focus spotting pipeline of human beings and impressive performances of Pre-trained Language Models (PLMs) on visual tasks, we ask: 1) "Can machines spot texts without precise detection just like human beings?", and if yes, 2) "Is text block another alternative for scene text spotting other than word or character?" To this end, our proposed scene text spotter leverages advanced PLMs to enhance performance without fine-grained detection. Specifically, we first use a simple detector for block-level text detection to obtain rough positional information. Then, we finetune a PLM using a large-scale OCR dataset to achieve accurate recognition. Benefiting from the comprehensive language knowledge gained during the pre-training phase, the PLM-based recognition module effectively handles complex scenarios, including multi-line, reversed, occluded, and incomplete-detection texts. Taking advantage of the fine-tuned language model on scene recognition benchmarks and the paradigm of text block detection, extensive experiments demonstrate the superior performance of our scene text spotter across multiple public benchmarks. Additionally, we attempt to spot texts directly from an entire scene image to demonstrate the potential of PLMs, even Large Language Models (LLMs).

Gengluo Li, Huawen Shen, Yu Zhou

Chinese scene text retrieval is a practical task that aims to search for images containing visual instances of a Chinese query text. This task is extremely challenging because Chinese text often features complex and diverse layouts in real-world scenes. Current efforts tend to inherit the solution for English scene text retrieval, failing to achieve satisfactory performance. In this paper, we establish a Diversified Layout benchmark for Chinese Street View Text Retrieval (DL-CSVTR), which is specifically designed to evaluate retrieval performance across various text layouts, including vertical, cross-line, and partial alignments. To address the limitations in existing methods, we propose Chinese Scene Text Retrieval CLIP (CSTR-CLIP), a novel model that integrates global visual information with multi-granularity alignment training. CSTR-CLIP applies a two-stage training process to overcome previous limitations, such as the exclusion of visual features outside the text region and reliance on single-granularity alignment, thereby enabling the model to effectively handle diverse text layouts. Experiments on existing benchmark show that CSTR-CLIP outperforms the previous state-of-the-art model by 18.82% accuracy and also provides faster inference speed. Further analysis on DL-CSVTR confirms the superior performance of CSTR-CLIP in handling various text layouts. The dataset and code will be publicly available to facilitate research in Chinese scene text retrieval.

Shuo Cao, Nan Ma, Jiayang Li et al.

The rapid advancement of educational applications, artistic creation, and AI-generated content (AIGC) technologies has substantially increased practical requirements for comprehensive Image Aesthetics Assessment (IAA), particularly demanding methods capable of delivering both quantitative scoring and professional understanding. Multimodal Large Language Model (MLLM)-based IAA methods demonstrate stronger perceptual and generalization capabilities compared to traditional approaches, yet they suffer from modality bias (score-only or text-only) and lack fine-grained attribute decomposition, thereby failing to support further aesthetic assessment. In this paper, we present:(1) ArtiMuse, an innovative MLLM-based IAA model with Joint Scoring and Expert-Level Understanding capabilities; (2) ArtiMuse-10K, the first expert-curated image aesthetic dataset comprising 10,000 images spanning 5 main categories and 15 subcategories, each annotated by professional experts with 8-dimensional attributes analysis and a holistic score. Both the model and dataset will be made public to advance the field.

Yu Zhou, Sha Li, Manling Li et al.

Online resources such as WikiHow compile a wide range of scripts for performing everyday tasks, which can assist models in learning to reason about procedures. However, the scripts are always presented in a linear manner, which does not reflect the flexibility displayed by people executing tasks in real life. For example, in the CrossTask Dataset, 64.5% of consecutive step pairs are also observed in the reverse order, suggesting their ordering is not fixed. In addition, each step has an average of 2.56 frequent next steps, demonstrating "branching". In this paper, we propose the new challenging task of non-sequential graph script induction, aiming to capture optional and interchangeable steps in procedural planning. To automate the induction of such graph scripts for given tasks, we propose to take advantage of loosely aligned videos of people performing the tasks. In particular, we design a multimodal framework to ground procedural videos to WikiHow textual steps and thus transform each video into an observed step path on the latent ground truth graph script. This key transformation enables us to train a script knowledge model capable of both generating explicit graph scripts for learnt tasks and predicting future steps given a partial step sequence. Our best model outperforms the strongest pure text/vision baselines by 17.52% absolute gains on F1@3 for next step prediction and 13.8% absolute gains on Acc@1 for partial sequence completion. Human evaluation shows our model outperforming the WikiHow linear baseline by 48.76% absolute gains in capturing sequential and non-sequential step relationships.

Xiaomeng Yang, Zhi Qiao, Jin Wei et al.

Scene Text Recognition (STR) is difficult because of the variations in text styles, shapes, and backgrounds. Though the integration of linguistic information enhances models' performance, existing methods based on either permuted language modeling (PLM) or masked language modeling (MLM) have their pitfalls. PLM's autoregressive decoding lacks foresight into subsequent characters, while MLM overlooks inter-character dependencies. Addressing these problems, we propose a masked and permuted implicit context learning network for STR, which unifies PLM and MLM within a single decoder, inheriting the advantages of both approaches. We utilize the training procedure of PLM, and to integrate MLM, we incorporate word length information into the decoding process and replace the undetermined characters with mask tokens. Besides, perturbation training is employed to train a more robust model against potential length prediction errors. Our empirical evaluations demonstrate the performance of our model. It not only achieves superior performance on the common benchmarks but also achieves a substantial improvement of $9.1\%$ on the more challenging Union14M-Benchmark.

Sky CH-Wang, Arkadiy Saakyan, Oliver Li et al.

Designing systems that can reason across cultures requires that they are grounded in the norms of the contexts in which they operate. However, current research on developing computational models of social norms has primarily focused on American society. Here, we propose a novel approach to discover and compare descriptive social norms across Chinese and American cultures. We demonstrate our approach by leveraging discussions on a Chinese Q&A platform (Zhihu) and the existing SocialChemistry dataset as proxies for contrasting cultural axes, align social situations cross-culturally, and extract social norms from texts using in-context learning. Embedding Chain-of-Thought prompting in a human-AI collaborative framework, we build a high-quality dataset of 3,069 social norms aligned with social situations across Chinese and American cultures alongside corresponding free-text explanations. To test the ability of models to reason about social norms across cultures, we introduce the task of explainable social norm entailment, showing that existing models under 3B parameters have significant room for improvement in both automatic and human evaluation. Further analysis of cross-cultural norm differences based on our dataset shows empirical alignment with the social orientations framework, revealing several situational and descriptive nuances in norms across these cultures.

Cong Ma, Yaping Zhang, Mei Tu et al.

Text image machine translation (TIMT) aims to translate texts embedded in images from one source language to another target language. Existing methods, both two-stage cascade and one-stage end-to-end architectures, suffer from different issues. The cascade models can benefit from the large-scale optical character recognition (OCR) and MT datasets but the two-stage architecture is redundant. The end-to-end models are efficient but suffer from training data deficiency. To this end, in our paper, we propose an end-to-end TIMT model fully making use of the knowledge from existing OCR and MT datasets to pursue both an effective and efficient framework. More specifically, we build a novel modal adapter effectively bridging the OCR encoder and MT decoder. End-to-end TIMT loss and cross-modal contrastive loss are utilized jointly to align the feature distribution of the OCR and MT tasks. Extensive experiments show that the proposed method outperforms the existing two-stage cascade models and one-stage end-to-end models with a lighter and faster architecture. Furthermore, the ablation studies verify the generalization of our method, where the proposed modal adapter is effective to bridge various OCR and MT models.

Zhou Yu, Lixiang Zheng, Zhou Zhao et al.

Building benchmarks to systemically analyze different capabilities of video question answering (VideoQA) models is challenging yet crucial. Existing benchmarks often use non-compositional simple questions and suffer from language biases, making it difficult to diagnose model weaknesses incisively. A recent benchmark AGQA poses a promising paradigm to generate QA pairs automatically from pre-annotated scene graphs, enabling it to measure diverse reasoning abilities with granular control. However, its questions have limitations in reasoning about the fine-grained semantics in videos as such information is absent in its scene graphs. To this end, we present ANetQA, a large-scale benchmark that supports fine-grained compositional reasoning over the challenging untrimmed videos from ActivityNet. Similar to AGQA, the QA pairs in ANetQA are automatically generated from annotated video scene graphs. The fine-grained properties of ANetQA are reflected in the following: (i) untrimmed videos with fine-grained semantics; (ii) spatio-temporal scene graphs with fine-grained taxonomies; and (iii) diverse questions generated from fine-grained templates. ANetQA attains 1.4 billion unbalanced and 13.4 million balanced QA pairs, which is an order of magnitude larger than AGQA with a similar number of videos. Comprehensive experiments are performed for state-of-the-art methods. The best model achieves 44.5% accuracy while human performance tops out at 84.5%, leaving sufficient room for improvement.

Rui Qiu, Zhou Yu, Ruoqing Zhu

Statistical analysis is increasingly confronted with complex data from metric spaces. Petersen and Müller (2019) established a general paradigm of Fréchet regression with complex metric space valued responses and Euclidean predictors. However, the local approach therein involves nonparametric kernel smoothing and suffers from the curse of dimensionality. To address this issue, we in this paper propose a novel random forest weighted local Fréchet regression paradigm. The main mechanism of our approach relies on a locally adaptive kernel generated by random forests. Our first method uses these weights as the local average to solve the conditional Fréchet mean, while the second method performs local linear Fréchet regression, both significantly improving existing Fréchet regression methods. Based on the theory of infinite order U-processes and infinite order $M_{m_n}$-estimator, we establish the consistency, rate of convergence, and asymptotic normality for our local constant estimator, which covers the current large sample theory of random forests with Euclidean responses as a special case. Numerical studies show the superiority of our methods with several commonly encountered types of responses such as distribution functions, symmetric positive-definite matrices, and sphere data. The practical merits of our proposals are also demonstrated through the application to New York taxi data and human mortality data.

Pan Lu, Liang Qiu, Jiaqi Chen et al.

Current visual question answering (VQA) tasks mainly consider answering human-annotated questions for natural images. However, aside from natural images, abstract diagrams with semantic richness are still understudied in visual understanding and reasoning research. In this work, we introduce a new challenge of Icon Question Answering (IconQA) with the goal of answering a question in an icon image context. We release IconQA, a large-scale dataset that consists of 107,439 questions and three sub-tasks: multi-image-choice, multi-text-choice, and filling-in-the-blank. The IconQA dataset is inspired by real-world diagram word problems that highlight the importance of abstract diagram understanding and comprehensive cognitive reasoning. Thus, IconQA requires not only perception skills like object recognition and text understanding, but also diverse cognitive reasoning skills, such as geometric reasoning, commonsense reasoning, and arithmetic reasoning. To facilitate potential IconQA models to learn semantic representations for icon images, we further release an icon dataset Icon645 which contains 645,687 colored icons on 377 classes. We conduct extensive user studies and blind experiments and reproduce a wide range of advanced VQA methods to benchmark the IconQA task. Also, we develop a strong IconQA baseline Patch-TRM that applies a pyramid cross-modal Transformer with input diagram embeddings pre-trained on the icon dataset. IconQA and Icon645 are available at https://iconqa.github.io.

Wei Wang, Yu Zhou, Jiahao Lv et al.

The research focus of scene text detection and recognition has shifted to arbitrary shape text in recent years, where the text shape representation is a fundamental problem. An ideal representation should be compact, complete, efficient, and reusable for subsequent recognition in our opinion. However, previous representations have flaws in one or more aspects. Thin-Plate-Spline (TPS) transformation has achieved great success in scene text recognition. Inspired by this, we reversely think of its usage and sophisticatedly take TPS as an exquisite representation for arbitrary shape text representation. The TPS representation is compact, complete, and efficient. With the predicted TPS parameters, the detected text region can be directly rectified to a near-horizontal one to assist the subsequent recognition. To further exploit the potential of the TPS representation, the Border Alignment Loss is proposed. Based on these designs, we implement the text detector TPSNet, which can be extended to a text spotter conveniently. Extensive evaluation and ablation of several public benchmarks demonstrate the effectiveness and superiority of the proposed method for text representation and spotting. Particularly, TPSNet achieves the detection F-Measure improvement of 4.4\% (78.4\% vs. 74.0\%) on Art dataset and the end-to-end spotting F-Measure improvement of 5.0\% (78.5\% vs. 73.5\%) on Total-Text, which are large margins with no bells and whistles.

Yuhao Cui, Zhou Yu, Chunqi Wang et al.

Vision-and-language pretraining (VLP) aims to learn generic multimodal representations from massive image-text pairs. While various successful attempts have been proposed, learning fine-grained semantic alignments between image-text pairs plays a key role in their approaches. Nevertheless, most existing VLP approaches have not fully utilized the intrinsic knowledge within the image-text pairs, which limits the effectiveness of the learned alignments and further restricts the performance of their models. To this end, we introduce a new VLP method called ROSITA, which integrates the cross- and intra-modal knowledge in a unified scene graph to enhance the semantic alignments. Specifically, we introduce a novel structural knowledge masking (SKM) strategy to use the scene graph structure as a priori to perform masked language (region) modeling, which enhances the semantic alignments by eliminating the interference information within and across modalities. Extensive ablation studies and comprehensive analysis verifies the effectiveness of ROSITA in semantic alignments. Pretrained with both in-domain and out-of-domain datasets, ROSITA significantly outperforms existing state-of-the-art VLP methods on three typical vision-and-language tasks over six benchmark datasets.

Mingyang Zhou, Luowei Zhou, Shuohang Wang et al.

Vision-and-language pre-training has achieved impressive success in learning multimodal representations between vision and language. To generalize this success to non-English languages, we introduce UC2, the first machine translation-augmented framework for cross-lingual cross-modal representation learning. To tackle the scarcity problem of multilingual captions for image datasets, we first augment existing English-only datasets with other languages via machine translation (MT). Then we extend the standard Masked Language Modeling and Image-Text Matching training objectives to multilingual setting, where alignment between different languages is captured through shared visual context (i.e, using image as pivot). To facilitate the learning of a joint embedding space of images and all languages of interest, we further propose two novel pre-training tasks, namely Masked Region-to-Token Modeling (MRTM) and Visual Translation Language Modeling (VTLM), leveraging MT-enhanced translated data. Evaluation on multilingual image-text retrieval and multilingual visual question answering benchmarks demonstrates that our proposed framework achieves new state-of-the-art on diverse non-English benchmarks while maintaining comparable performance to monolingual pre-trained models on English tasks.

Dian Yu, Zhou Yu, Kenji Sagae

Large language models benefit from training with a large amount of unlabeled text, which gives them increasingly fluent and diverse generation capabilities. However, using these models for text generation that takes into account target attributes, such as sentiment polarity or specific topics, remains a challenge. We propose a simple and flexible method for controlling text generation by aligning disentangled attribute representations. In contrast to recent efforts on training a discriminator to perturb the token level distribution for an attribute, we use the same data to learn an alignment function to guide the pre-trained, non-controlled language model to generate texts with the target attribute without changing the original language model parameters. We evaluate our method on sentiment- and topic-controlled generation, and show large performance gains over previous methods while retaining fluency and diversity.

Weiyan Shi, Yu Li, Saurav Sahay et al.

Persuasion dialogue systems reflect the machine's ability to make strategic moves beyond verbal communication, and therefore differentiate themselves from task-oriented or open-domain dialogue systems and have their own unique values. However, the repetition and inconsistency problems still persist in dialogue response generation and could substantially impact user experience and impede the persuasion outcome. Besides, although reinforcement learning (RL) approaches have achieved big success in strategic tasks such as games, they require a sophisticated user simulator to provide real-time feedback to the dialogue system, which limits the application of RL on persuasion dialogues. To address these issues towards a better persuasion dialogue system, we apply RL to refine a language model baseline without user simulators, and distill sentence-level information about repetition, inconsistency, and task relevance through rewards. Moreover, to better accomplish the persuasion task, the model learns from human demonstration to imitate human persuasion behavior and selects the most persuasive responses. Experiments show that our model outperforms previous state-of-the-art dialogue models on both automatic metrics and human evaluation results on a donation persuasion task, and generates more diverse, consistent and persuasive conversations according to the user feedback.

Weixin Liang, James Zou, Zhou Yu

Training a supervised neural network classifier typically requires many annotated training samples. Collecting and annotating a large number of data points are costly and sometimes even infeasible. Traditional annotation process uses a low-bandwidth human-machine communication interface: classification labels, each of which only provides several bits of information. We propose Active Learning with Contrastive Explanations (ALICE), an expert-in-the-loop training framework that utilizes contrastive natural language explanations to improve data efficiency in learning. ALICE learns to first use active learning to select the most informative pairs of label classes to elicit contrastive natural language explanations from experts. Then it extracts knowledge from these explanations using a semantic parser. Finally, it incorporates the extracted knowledge through dynamically changing the learning model's structure. We applied ALICE in two visual recognition tasks, bird species classification and social relationship classification. We found by incorporating contrastive explanations, our models outperform baseline models that are trained with 40-100% more training data. We found that adding 1 explanation leads to similar performance gain as adding 13-30 labeled training data points.

Dezhao Luo, Bo Fang, Yu Zhou et al.

Existing video self-supervised learning methods mainly rely on trimmed videos for model training. However, trimmed datasets are manually annotated from untrimmed videos. In this sense, these methods are not really self-supervised. In this paper, we propose a novel self-supervised method, referred to as Exploring Relations in Untrimmed Videos (ERUV), which can be straightforwardly applied to untrimmed videos (real unlabeled) to learn spatio-temporal features. ERUV first generates single-shot videos by shot change detection. Then a designed sampling strategy is used to model relations for video clips. The strategy is saved as our self-supervision signals. Finally, the network learns representations by predicting the category of relations between the video clips. ERUV is able to compare the differences and similarities of videos, which is also an essential procedure for action and video related tasks. We validate our learned models with action recognition and video retrieval tasks with three kinds of 3D CNNs. Experimental results show that ERUV is able to learn richer representations and it outperforms state-of-the-art self-supervised methods with significant margins.

Weixin Liang, James Zou, Zhou Yu

Open Domain dialog system evaluation is one of the most important challenges in dialog research. Existing automatic evaluation metrics, such as BLEU are mostly reference-based. They calculate the difference between the generated response and a limited number of available references. Likert-score based self-reported user rating is widely adopted by social conversational systems, such as Amazon Alexa Prize chatbots. However, self-reported user rating suffers from bias and variance among different users. To alleviate this problem, we formulate dialog evaluation as a comparison task. We also propose an automatic evaluation model CMADE (Comparison Model for Automatic Dialog Evaluation) that automatically cleans self-reported user ratings as it trains on them. Specifically, we first use a self-supervised method to learn better dialog feature representation, and then use KNN and Shapley to remove confusing samples. Our experiments show that CMADE achieves 89.2% accuracy in the dialog comparison task.

Zhou Yu, Yuhao Cui, Jun Yu et al.

Designing effective neural networks is fundamentally important in deep multimodal learning. Most existing works focus on a single task and design neural architectures manually, which are highly task-specific and hard to generalize to different tasks. In this paper, we devise a generalized deep multimodal neural architecture search (MMnas) framework for various multimodal learning tasks. Given multimodal input, we first define a set of primitive operations, and then construct a deep encoder-decoder based unified backbone, where each encoder or decoder block corresponds to an operation searched from a predefined operation pool. On top of the unified backbone, we attach task-specific heads to tackle different multimodal learning tasks. By using a gradient-based NAS algorithm, the optimal architectures for different tasks are learned efficiently. Extensive ablation studies, comprehensive analysis, and comparative experimental results show that the obtained MMnasNet significantly outperforms existing state-of-the-art approaches across three multimodal learning tasks (over five datasets), including visual question answering, image-text matching, and visual grounding.

Silin Gao, Yichi Zhang, Zhijian Ou et al.

Neural generative models have achieved promising performance on dialog generation tasks if given a huge data set. However, the lack of high-quality dialog data and the expensive data annotation process greatly limit their application in real-world settings. We propose a paraphrase augmented response generation (PARG) framework that jointly trains a paraphrase model and a response generation model to improve the dialog generation performance. We also design a method to automatically construct paraphrase training data set based on dialog state and dialog act labels. PARG is applicable to various dialog generation models, such as TSCP (Lei et al., 2018) and DAMD (Zhang et al., 2019). Experimental results show that the proposed framework improves these state-of-the-art dialog models further on CamRest676 and MultiWOZ. PARG also significantly outperforms other data augmentation methods in dialog generation tasks, especially under low resource settings.

Yijun Song, Jingwen Wang, Lin Ma et al.

The task of temporally grounding textual queries in videos is to localize one video segment that semantically corresponds to the given query. Most of the existing approaches rely on segment-sentence pairs (temporal annotations) for training, which are usually unavailable in real-world scenarios. In this work we present an effective weakly-supervised model, named as Multi-Level Attentional Reconstruction Network (MARN), which only relies on video-sentence pairs during the training stage. The proposed method leverages the idea of attentional reconstruction and directly scores the candidate segments with the learnt proposal-level attentions. Moreover, another branch learning clip-level attention is exploited to refine the proposals at both the training and testing stage. We develop a novel proposal sampling mechanism to leverage intra-proposal information for learning better proposal representation and adopt 2D convolution to exploit inter-proposal clues for learning reliable attention map. Experiments on Charades-STA and ActivityNet-Captions datasets demonstrate the superiority of our MARN over the existing weakly-supervised methods.

Lin Yuan, Zhou Yu

The demand for abstractive dialog summary is growing in real-world applications. For example, customer service center or hospitals would like to summarize customer service interaction and doctor-patient interaction. However, few researchers explored abstractive summarization on dialogs due to the lack of suitable datasets. We propose an abstractive dialog summarization dataset based on MultiWOZ. If we directly apply previous state-of-the-art document summarization methods on dialogs, there are two significant drawbacks: the informative entities such as restaurant names are difficult to preserve, and the contents from different dialog domains are sometimes mismatched. To address these two drawbacks, we propose Scaffold Pointer Network (SPNet)to utilize the existing annotation on speaker role, semantic slot and dialog domain. SPNet incorporates these semantic scaffolds for dialog summarization. Since ROUGE cannot capture the two drawbacks mentioned, we also propose a new evaluation metric that considers critical informative entities in the text. On MultiWOZ, our proposed SPNet outperforms state-of-the-art abstractive summarization methods on all the automatic and human evaluation metrics.

Mingyang Zhou, Josh Arnold, Zhou Yu

Reinforcement learning (RL) is an effective approach to learn an optimal dialog policy for task-oriented visual dialog systems. A common practice is to apply RL on a neural sequence-to-sequence (seq2seq) framework with the action space being the output vocabulary in the decoder. However, it is difficult to design a reward function that can achieve a balance between learning an effective policy and generating a natural dialog response. This paper proposes a novel framework that alternatively trains a RL policy for image guessing and a supervised seq2seq model to improve dialog generation quality. We evaluate our framework on the GuessWhich task and the framework achieves the state-of-the-art performance in both task completion and dialog quality.

Zhou Yu, Yuhao Cui, Jun Yu et al.

Learning an effective attention mechanism for multimodal data is important in many vision-and-language tasks that require a synergic understanding of both the visual and textual contents. Existing state-of-the-art approaches use co-attention models to associate each visual object (e.g., image region) with each textual object (e.g., query word). Despite the success of these co-attention models, they only model inter-modal interactions while neglecting intra-modal interactions. Here we propose a general `unified attention' model that simultaneously captures the intra- and inter-modal interactions of multimodal features and outputs their corresponding attended representations. By stacking such unified attention blocks in depth, we obtain the deep Multimodal Unified Attention Network (MUAN), which can seamlessly be applied to the visual question answering (VQA) and visual grounding tasks. We evaluate our MUAN models on two VQA datasets and three visual grounding datasets, and the results show that MUAN achieves top-level performance on both tasks without bells and whistles.

Kun Qian, Zhou Yu

Domain adaptation is an essential task in dialog system building because there are so many new dialog tasks created for different needs every day. Collecting and annotating training data for these new tasks is costly since it involves real user interactions. We propose a domain adaptive dialog generation method based on meta-learning (DAML). DAML is an end-to-end trainable dialog system model that learns from multiple rich-resource tasks and then adapts to new domains with minimal training samples. We train a dialog system model using multiple rich-resource single-domain dialog data by applying the model-agnostic meta-learning algorithm to dialog domain. The model is capable of learning a competitive dialog system on a new domain with only a few training examples in an efficient manner. The two-step gradient updates in DAML enable the model to learn general features across multiple tasks. We evaluate our method on a simulated dialog dataset and achieve state-of-the-art performance, which is generalizable to new tasks.

Jun Yu, Jing Li, Zhou Yu et al.

Image captioning aims to automatically generate a natural language description of a given image, and most state-of-the-art models have adopted an encoder-decoder framework. The framework consists of a convolution neural network (CNN)-based image encoder that extracts region-based visual features from the input image, and an recurrent neural network (RNN)-based caption decoder that generates the output caption words based on the visual features with the attention mechanism. Despite the success of existing studies, current methods only model the co-attention that characterizes the inter-modal interactions while neglecting the self-attention that characterizes the intra-modal interactions. Inspired by the success of the Transformer model in machine translation, here we extend it to a Multimodal Transformer (MT) model for image captioning. Compared to existing image captioning approaches, the MT model simultaneously captures intra- and inter-modal interactions in a unified attention block. Due to the in-depth modular composition of such attention blocks, the MT model can perform complex multimodal reasoning and output accurate captions. Moreover, to further improve the image captioning performance, multi-view visual features are seamlessly introduced into the MT model. We quantitatively and qualitatively evaluate our approach using the benchmark MSCOCO image captioning dataset and conduct extensive ablation studies to investigate the reasons behind its effectiveness. The experimental results show that our method significantly outperforms the previous state-of-the-art methods. With an ensemble of seven models, our solution ranks the 1st place on the real-time leaderboard of the MSCOCO image captioning challenge at the time of the writing of this paper.

Jun Yu, Jinghan Yao, Jian Zhang et al.

Object instance segmentation is one of the most fundamental but challenging tasks in computer vision, and it requires the pixel-level image understanding. Most existing approaches address this problem by adding a mask prediction branch to a two-stage object detector with the Region Proposal Network (RPN). Although producing good segmentation results, the efficiency of these two-stage approaches is far from satisfactory, restricting their applicability in practice. In this paper, we propose a one-stage framework, SPRNet, which performs efficient instance segmentation by introducing a single pixel reconstruction (SPR) branch to off-the-shelf one-stage detectors. The added SPR branch reconstructs the pixel-level mask from every single pixel in the convolution feature map directly. Using the same ResNet-50 backbone, SPRNet achieves comparable mask AP to Mask R-CNN at a higher inference speed, and gains all-round improvements on box AP at every scale comparing with RetinaNet.

Mingyang Zhou, Runxiang Cheng, Yong Jae Lee et al.

We introduce a novel multimodal machine translation model that utilizes parallel visual and textual information. Our model jointly optimizes the learning of a shared visual-language embedding and a translator. The model leverages a visual attention grounding mechanism that links the visual semantics with the corresponding textual semantics. Our approach achieves competitive state-of-the-art results on the Multi30K and the Ambiguous COCO datasets. We also collected a new multilingual multimodal product description dataset to simulate a real-world international online shopping scenario. On this dataset, our visual attention grounding model outperforms other methods by a large margin.

Weiming Wen, Songwen Su, Zhou Yu

With the increasing popularity of smart devices, rumors with multimedia content become more and more common on social networks. The multimedia information usually makes rumors look more convincing. Therefore, finding an automatic approach to verify rumors with multimedia content is a pressing task. Previous rumor verification research only utilizes multimedia as input features. We propose not to use the multimedia content but to find external information in other news platforms pivoting on it. We introduce a new features set, cross-lingual cross-platform features that leverage the semantic similarity between the rumors and the external information. When implemented, machine learning methods utilizing such features achieved the state-of-the-art rumor verification results.