Building cross-model intelligence that can understand charts and communicate the salient information hidden behind them is an appealing challenge in the vision and language (V+L) community. The capability to uncover the underlined table data of chart figures is a critical key to automatic chart understanding. We introduce ChartT5, a V+L model that learns how to interpret table information from chart images via cross-modal pre-training on plot table pairs. Specifically, we propose two novel pre-training objectives: Masked Header Prediction (MHP) and Masked Value Prediction (MVP) to facilitate the model with different skills to interpret the table information. We have conducted extensive experiments on chart question answering and chart summarization to verify the effectiveness of the proposed pre-training strategies. In particular, on the ChartQA benchmark, our ChartT5 outperforms the state-of-the-art non-pretraining methods by over 8% performance gains.
Vision-language (VL) understanding tasks evaluate models’ comprehension of complex visual scenes through multiple-choice questions. However, we have identified two dataset biases that models can exploit as shortcuts to resolve various VL tasks correctly without proper understanding. The first type of dataset bias is Unbalanced Matching bias, where the correct answer overlaps the question and image more than the incorrect answers. The second type of dataset bias is Distractor Similarity bias, where incorrect answers are overly dissimilar to the correct answer but significantly similar to other incorrect answers within the same sample. To address these dataset biases, we first propose Adversarial Data Synthesis (ADS) to generate synthetic training and debiased evaluation data. We then introduce Intra-sample Counterfactual Training (ICT) to assist models in utilizing the synthesized training data, particularly the counterfactual data, via focusing on intra-sample differentiation. Extensive experiments demonstrate the effectiveness of ADS and ICT in consistently improving model performance across different benchmarks, even in domain-shifted scenarios.
The age of social media is rife with memes. Understanding and detecting harmful memes pose a significant challenge due to their implicit meaning that is not explicitly conveyed through the surface text and image. However, existing harmful meme detection approaches only recognize superficial harm-indicative signals in an end-to-end classification manner but ignore in-depth cognition of the meme text and image. In this paper, we attempt to detect harmful memes based on advanced reasoning over the interplay of multimodal information in memes. Inspired by the success of Large Language Models (LLMs) on complex reasoning, we first conduct abductive reasoning with LLMs. Then we propose a novel generative framework to learn reasonable thoughts from LLMs for better multimodal fusion and lightweight fine-tuning, which consists of two training stages: 1) Distill multimodal reasoning knowledge from LLMs; and 2) Fine-tune the generative framework to infer harmfulness. Extensive experiments conducted on three meme datasets demonstrate that our proposed approach achieves superior performance than state-of-the-art methods on the harmful meme detection task.
The field of vision-and-language (VL) understanding has made unprecedented progress with end-to-end large pre-trained VL models (VLMs). However, they still fall short in zero-shot reasoning tasks that require multi-step inferencing. To achieve this goal, previous works resort to a divide-and-conquer pipeline. In this paper, we argue that previous efforts have several inherent shortcomings: 1) They rely on domain-specific sub-question decomposing models. 2) They force models to predict the final answer even if the sub-questions or sub-answers provide insufficient information. We address these limitations via IdealGPT, a framework that iteratively decomposes VL reasoning using large language models (LLMs). Specifically, IdealGPT utilizes an LLM to generate sub-questions, a VLM to provide corresponding sub-answers, and another LLM to reason to achieve the final answer. These three modules perform the divide-and-conquer procedure iteratively until the model is confident about the final answer to the main question. We evaluate IdealGPT on multiple challenging VL reasoning tasks under a zero-shot setting. In particular, our IdealGPT outperforms the best existing GPT-4-like models by an absolute 10% on VCR and 15% on SNLI-VE. Code is available at https://github.com/Hxyou/IdealGPT.
Identifying semantic argument types in predication contexts is not a straightforward task for several reasons, such as inherent polysemy, coercion, and copredication phenomena. In this paper, we train monolingual and multilingual classifiers with a zero-shot cross-lingual approach to identify semantic argument types in predications using pre-trained language models as feature extractors. We train classifiers for different semantic argument types and for both verbal and adjectival predications. Furthermore, we propose a method to detect copredication using these classifiers through identifying the argument semantic type targeted in different predications over the same noun in a sentence. We evaluate the performance of the method on copredication test data with Food•Event nouns for 5 languages.
Reasoning about causal and temporal event relations in videos is a new destination of Video Question Answering (VideoQA). The major stumbling block to achieve this purpose is the semantic gap between language and video since they are at different levels of abstraction. Existing efforts mainly focus on designing sophisticated architectures while utilizing frame- or object-level visual representations. In this paper, we reconsider the multi-modal alignment problem in VideoQA from feature and sample perspectives to achieve better performance. From the view of feature, we break down the video into trajectories and first leverage trajectory feature in VideoQA to enhance the alignment between two modalities. Moreover, we adopt a heterogeneous graph architecture and design a hierarchical framework to align both trajectory-level and frame-level visual feature with language feature. In addition, we found that VideoQA models are largely dependent on languagepriors and always neglect visual-language interactions. Thus, two effective yet portable training augmentation strategies are designed to strengthen the cross-modal correspondence ability of our model from the view of sample. Extensive results show that our method outperforms all the state-of the-art models on the challenging NExT-QA benchmark.
Given a long untrimmed video and natural language queries, video grounding (VG) aims to temporally localize the semantically-aligned video segments. Almost all existing VG work holds two simple but unrealistic assumptions: 1) All query sentences can be grounded in the corresponding video. 2) All query sentences for the same video are always at the same semantic scale. Unfortunately, both assumptions make today’s VG models fail to work in practice. For example, in real-world multimodal assets (eg, news articles), most of the sentences in the article can not be grounded in their affiliated videos, and they typically have rich hierarchical relations (ie, at different semantic scales). To this end, we propose a new challenging grounding task: Weakly-Supervised temporal Article Grounding (WSAG). Specifically, given an article and a relevant video, WSAG aims to localize all “groundable” sentences to the video, and these sentences are possibly at different semantic scales. Accordingly, we collect the first WSAG dataset to facilitate this task: YouwikiHow, which borrows the inherent multi-scale descriptions in wikiHow articles and plentiful YouTube videos. In addition, we propose a simple but effective method DualMIL for WSAG, which consists of a two-level MIL loss and a single-/cross- sentence constraint loss. These training objectives are carefully designed for these relaxed assumptions. Extensive ablations have verified the effectiveness of DualMIL.
Given an untrimmed video and a natural language query, Natural Language Video Localization (NLVL) aims to identify the video moment described by query. To address this task, existing methods can be roughly grouped into two groups: 1) propose-and-rank models first define a set of hand-designed moment candidates and then find out the best-matching one. 2) proposal-free models directly predict two temporal boundaries of the referential moment from frames. Currently, almost all the propose-and-rank methods have inferior performance than proposal-free counterparts. In this paper, we argue that the performance of propose-and-rank models are underestimated due to the predefined manners: 1) Hand-designed rules are hard to guarantee the complete coverage of targeted segments. 2) Densely sampled candidate moments cause redundant computation and degrade the performance of ranking process. To this end, we propose a novel model termed LPNet (Learnable Proposal Network for NLVL) with a fixed set of learnable moment proposals. The position and length of these proposals are dynamically adjusted during training process. Moreover, a boundary-aware loss has been proposed to leverage frame-level information and further improve performance. Extensive ablations on two challenging NLVL benchmarks have demonstrated the effectiveness of LPNet over existing state-of-the-art methods.
Video grounding aims to localize the temporal segment corresponding to a sentence query from an untrimmed video. Almost all existing video grounding methods fall into two frameworks: 1) Top-down model: It predefines a set of segment candidates and then conducts segment classification and regression. 2) Bottom-up model: It directly predicts frame-wise probabilities of the referential segment boundaries. However, all these methods are not end-to-end, i.e., they always rely on some time-consuming post-processing steps to refine predictions. To this end, we reformulate video grounding as a set prediction task and propose a novel end-to-end multi-modal Transformer model, dubbed as GTR. Specifically, GTR has two encoders for video and language encoding, and a cross-modal decoder for grounding prediction. To facilitate the end-to-end training, we use a Cubic Embedding layer to transform the raw videos into a set of visual tokens. To better fuse these two modalities in the decoder, we design a new Multi-head Cross-Modal Attention. The whole GTR is optimized via a Many-to-One matching loss. Furthermore, we conduct comprehensive studies to investigate different model design choices. Extensive results on three benchmarks have validated the superiority of GTR. All three typical GTR variants achieve record-breaking performance on all datasets and metrics, with several times faster inference speed.
Legal Judgement Prediction (LJP) is the task of automatically predicting a law case’s judgment results given a text describing the case’s facts, which has great prospects in judicial assistance systems and handy services for the public. In practice, confusing charges are often presented, because law cases applicable to similar law articles are easily misjudged. To address this issue, existing work relies heavily on domain experts, which hinders its application in different law systems. In this paper, we present an end-to-end model, LADAN, to solve the task of LJP. To distinguish confusing charges, we propose a novel graph neural network, GDL, to automatically learn subtle differences between confusing law articles, and also design a novel attention mechanism that fully exploits the learned differences to attentively extract effective discriminative features from fact descriptions. Experiments conducted on real-world datasets demonstrate the superiority of our LADAN.
In practical scenario, relation extraction needs to first identify entity pairs that have relation and then assign a correct relation class. However, the number of non-relation entity pairs in context (negative instances) usually far exceeds the others (positive instances), which negatively affects a model’s performance. To mitigate this problem, we propose a multi-task architecture which jointly trains a model to perform relation identification with cross-entropy loss and relation classification with ranking loss. Meanwhile, we observe that a sentence may have multiple entities and relation mentions, and the patterns in which the entities appear in a sentence may contain useful semantic information that can be utilized to distinguish between positive and negative instances. Thus we further incorporate the embeddings of character-wise/word-wise BIO tag from the named entity recognition task into character/word embeddings to enrich the input representation. Experiment results show that our proposed approach can significantly improve the performance of a baseline model with more than 10% absolute increase in F1-score, and outperform the state-of-the-art models on ACE 2005 Chinese and English corpus. Moreover, BIO tag embeddings are particularly effective and can be used to improve other models as well.
In this paper, we focus on natural language video localization: localizing (ie, grounding) a natural language description in a long and untrimmed video sequence. All currently published models for addressing this problem can be categorized into two types: (i) top-down approach: it does classification and regression for a set of pre-cut video segment candidates; (ii) bottom-up approach: it directly predicts probabilities for each video frame as the temporal boundaries (ie, start and end time point). However, both two approaches suffer several limitations: the former is computation-intensive for densely placed candidates, while the latter has trailed the performance of the top-down counterpart thus far. To this end, we propose a novel dense bottom-up framework: DEnse Bottom-Up Grounding (DEBUG). DEBUG regards all frames falling in the ground truth segment as foreground, and each foreground frame regresses the unique distances from its location to bi-directional ground truth boundaries. Extensive experiments on three challenging benchmarks (TACoS, Charades-STA, and ActivityNet Captions) show that DEBUG is able to match the speed of bottom-up models while surpassing the performance of the state-of-the-art top-down models.