In this work, we propose an efficient Video-Language Alignment (ViLA) network. Our ViLA model addresses both efficient frame sampling and effective cross-modal alignment in a unified way. In our ViLA network, we design a new learnable text-guided Frame-Prompter together with a new cross-modal distillation (QFormer-Distiller) module. Pre-trained large image-language models have shown promising results on problems such as visual question answering (VQA). However, how to efficiently and effectively sample video frames when adapting pre-trained large image-language model to video-language alignment is still the major challenge. Compared with prior work, our ViLA model demonstrates the capability of selecting key frames with critical contents, thus improving the video-language alignment accuracy while reducing the inference latency +3.3% on NExT-QA Temporal with 3.0X speed up). Overall, our ViLA network outperforms the state-of-the-art methods on the video question-answering benchmarks: +4.6% on STAR Interaction, +2.2% on STAR average with 3.0X speed up, ours 2-frames out-perform SeViLA 4-frames on the VLEP dataset with 4.2X speed-up. The code will be available at https://github.com/xijun-cs/ViLA.
Renmin University of China（中国人民大学）；University of Science and Technology of China（中国科学技术大学）；Microsoft Research（微软研究院）
Large-scale video-language pre-training has shown significant improvement in video-language understanding tasks. Previous studies of video-language pretraining mainly focus on short-form videos (i.e., within 30 seconds) and sentences, leaving long-form video-language pre-training rarely explored. Directly learning representation from long-form videos and language may benefit many long-form video-language understanding tasks. However, it is challenging due to the difficulty of modeling long-range relationships and the heavy computational burden caused by more frames. In this paper, we introduce…
National University of Singapore（新加坡国立大学）；University of Science and Technology of China（中国科学技术大学）
Video Question Answering (VideoQA) is the task of answering questions about a video. At its core is understanding the alignments between visual scenes in video and linguistic semantics in question to yield the answer. In leading VideoQA models, the typical learning objective, empirical risk minimization (ERM), latches on superficial correlations between video-question pairs and answers as the alignments. However, ERM can be problematic, because it tends to over-exploit the spurious correlations between question-irrelevant scenes and answers, instead of inspecting the causal effect of question-…
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 t…
A key challenge in video question answering is how to realize the cross-modal semantic alignment between textual concepts and corresponding visual objects. Existing methods mostly seek to align the word representations with the video regions. However, word representations are often not able to convey a complete description of textual concepts, which are in general described by the compositions of certain words. To address this issue, we propose to first build a syntactic dependency tree for each question with an off-the-shelf tool and use it to guide the extraction of meaningful word compositi…
Building a universal Video-Language model for solving various video understanding tasks (\emph{e.g.}, text-video retrieval, video question answering) is an open challenge to the machine learning field. Towards this goal, most recent works build the model by stacking uni-modal and cross-modal feature encoders and train it with pair-wise contrastive pre-text tasks. Though offering attractive generality, the resulted models have to compromise between efficiency and performance. They mostly adopt different architectures to deal with different downstream tasks. We find this is because the pair-wise…
Video-Language Alignment via Spatio-Temporal Graph Transformer
School of Computer and Communication Engineering, University of Science and Technology Beijing (USTB)（北京科技大学计算机与通信工程学院）；Institute of Artificial Intelligence, University of Science and Technology Beijing (USTB)（北京科技大学人工智能研究院）；USTB-EEasyTech Joint Lab of Artificial Intelligence（北京科技大学-易智科技人工智能联合实验室）；Tencent Hunyuan（腾讯混元）；Tencent（腾讯）；Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）
National Taiwan University（台湾大学）；Mobile Drive Technology（Mobile Drive科技公司）
While recent large-scale video-language pre-training made great progress in video question answering, the design of spatial modeling of video-language models is less fine-grained than that of image-language models; existing practices of temporal modeling also suffer from weak and noisy alignment between modalities. To learn fine-grained visual understanding, we decouple spatial-temporal modeling and propose a hybrid pipeline, Decoupled Spatial-Temporal Encoders, integrating an image- and a video-language encoder. The former encodes spatial semantics from larger but sparsely sampled frames inde…
Korea Advanced Institute of Science and Technology（韩国科学技术院）；Samsung Electronics（三星电子）
This paper proposes a method to gain extra supervision via multi-task learning for multi-modal video question answering. Multi-modal video question answering is an important task that aims at the joint understanding of vision and language. However, establishing large scale dataset for multi-modal video question answering is expensive and the existing benchmarks are relatively small to provide sufficient supervision. To overcome this challenge, this paper proposes a multi-task learning method which is composed of three main components: (1) multi-modal video question answering network that answe…
Visual Question Answering (VQA) attracts much attention from both industry and academia. As a multi-modality task, it is challenging since it requires not only visual and textual understanding, but also the ability to align cross-modality representations. Previous approaches extensively employ entity-level alignments, such as the correlations between the visual regions and their semantic labels, or the interactions across question words and object features. These attempts aim to improve the cross-modality representations, while ignoring their internal relations. Instead, we propose to apply st…
Northwestern University（西北大学）；Samsung Research America（三星美国研究院）
Learning to answer visual questions is a challenging task since the multi-modal inputs are within two feature spaces. Moreover, reasoning in visual question answering requires the model to understand both image and question, and align them in the same space, rather than simply memorize statistics about the question-answer pairs. Thus, it is essential to find component connections between different modalities and within each modality to achieve better attention. Previous works learned attention weights directly on the features. However, the improvement is limited since these two modality featur…
The ideal form of Visual Question Answering requires understanding, grounding and reasoning in the joint space of vision and language and serves as a proxy for the AI task of scene understanding. However, most existing VQA benchmarks are limited to just picking the answer from a pre-defined set of options and lack attention to text. We present a new challenge with a dataset that contains 23,781 questions based on 10124 image-text pairs. Specifically, the task requires the model to align multimedia representations of the same entity to implement multi-hop reasoning between image and text and fi…
A$^2$Safe: Counterfactual Evidence-Aligned Adaptive Agent Collaboration for Safe and Effective Visual Question Answering
Macau University of Science and Technology（澳门科技大学）；Wuhan University of Technology（武汉理工大学）；Nanjing Institute of Technology（南京工程学院）；National Tsing Hua University（国立清华大学）
Technical University of Kaiserslautern（凯泽斯劳滕工业大学）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）
Generating images from textual descriptions has recently attracted a lot of interest. While current models can generate photo-realistic images of individual objects such as birds and human faces, synthesising images with multiple objects is still very difficult. In this paper, we propose an effective way to combine Text-to-Image (T2I) synthesis with Visual Question Answering (VQA) to improve the image quality and image-text alignment of generated images by leveraging the VQA 2.0 dataset. We create additional training samples by concatenating question and answer (QA) pairs and employ a standard…
We propose a new 3D spatial understanding task of 3D Question Answering (3D-QA). In the 3D-QA task, models receive visual information from the entire 3D scene of the rich RGB-D indoor scan and answer the given textual questions about the 3D scene. Unlike the 2D-question answering of VQA, the conventional 2D-QA models suffer from problems with spatial understanding of object alignment and directions and fail the object identification from the textual questions in 3D-QA. We propose a baseline model for 3D-QA, named ScanQA model, where the model learns a fused descriptor from 3D object proposals …
Tianjin University（天津大学）；Hefei University of Technology（合肥工业大学）
Movies provide us with a mass of visual content as well as attracting stories. Existing methods have illustrated that understanding movie stories through only visual content is still a hard problem. In this paper, for answering questions about movies, we put forward a Layered Memory Network (LMN) that represents frame-level and clip-level movie content by the Static Word Memory module and the Dynamic Subtitle Memory module, respectively. Particularly, we firstly extract words and sentences from the training movie subtitles. Then the hierarchically formed movie representations, which are learne…
Object Attribute Matters in Visual Question Answering
Jilin University（吉林大学）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Saliency Guided Longitudinal Medical Visual Question Answering
Dept. of Computer Science and Engineering University of California, San Diego（计算机科学与工程系，加州大学圣地亚哥分校）；Dept. of Radiology and Biomedical Imaging Yale University（放射学与生物医学成像系，耶鲁大学）
Medical image visual question answering (VQA) is a task to answer clinical questions, given a radiographic image, which is a challenging problem that requires a model to integrate both vision and language information. To solve medical VQA problems with a limited number of training data, pretrain-finetune paradigm is widely used to improve the model generalization. In this paper, we propose a self-supervised method that applies Masked image modeling, Masked language modeling, Image text matching and Image text alignment via contrastive learning (M2I2) for pretraining on medical image caption da…
mChartQA: A universal benchmark for multimodal Chart Question Answer based on Vision-Language Alignment and Reasoning
Shenyang Institute of Computing Technology, Chinese Academy of Sciences（中国科学院沈阳计算技术研究所）；Beijing Wenge Technology Co., Ltd（北京文格科技有限公司）；University of Chinese Academy of Sciences（中国科学院大学）
Look Clearly Before Answering: Mitigating Hallucinations in LVLMs via Saliency-Driven Perceptual Realignment
Xidian University（西安电子科技大学）；Tsinghua University（清华大学）；Shanghai Road Transport Development Center（上海市道路运输发展中心）；Hunan Institute of Advanced Technology（湖南先进技术研究院）
SKLCCSE, School of Artificial Intelligence, Beihang University, Beijing, China（北京航空航天大学人工智能学院）；Hangzhou International Innovation Institute, Beihang University, Hangzhou, China（北京航空航天大学杭州国际创新研究院）
CMI-MTL: Cross-Mamba interaction based multi-task learning for medical visual question answering
School of Software, Northwestern Polytechnical University, Shaanxi, China（西北工业大学软件学院）；Yangtze River Delta Research Institute of Northwestern Polytechnical University, Taicang, China（西北工业大学长江三角研究 institute）；Department of Computer Science and Information Technology, La Trobe University, Melbourne, Australia（拉筹伯大学计算机科学与信息技术系）；CSIRO Data61, Sydney, Australia（CSIRO Data61）；School of Intelligence Science and Technology, Nanjing University, Suzhou, China（南京大学智能科学与技术学院）；Australian Institute of Health Innovation (AIHI), Macquarie University, Australia（麦考瑞大学健康创新研究所）；School of Computer Software, College of Intelligence and Computing, Tianjin University, Tianjin, China（天津大学计算机软件学院）；Centre for Artificial Intelligence driven Drug Discovery, Faculty of Applied Science, Macao Polytechnic University, Macao Special Administrative Region of China（澳门理工学院人工智能驱动药物发现中心）；Department of Computer Science, School of Engineering, Shantou University, Guangdong, China（汕头大学计算机科学系）
MM-Prompt: Cross-Modal Prompt Tuning for Continual Visual Question Answering
Khoury College of Computer Sciences, Northeastern University（东北大学克劳尔计算机科学学院）；New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别新实验室）
Vision-and-language tasks are gaining popularity in the research community, but the focus is still mainly on English. We propose a pipeline that utilizes English-only vision-language models to train a monolingual model for a target language. We propose to extend OSCAR+, a model which leverages object tags as anchor points for learning image-text alignments, to train on visual question answering datasets in different languages. We propose a novel approach to knowledge distillation to train the model in other languages using parallel sentences. Compared to other models that use the target langua…
