We introduce FlexCap, a vision-language model that generates region-specific descriptions of varying lengths. FlexCap is trained to produce length-conditioned captions for input boxes, enabling control over information density, with descriptions ranging from concise object labels to detailed captions. To achieve this, we create large-scale training datasets of image region descriptions with varying lengths from captioned web images. We demonstrate FlexCap's effectiveness in several applications: first, it achieves strong performance in dense captioning tasks on the Visual Genome dataset. Second, we show how FlexCap's localized descriptions can serve as input to a large language model to create a visual question answering (VQA) system, achieving state-of-the-art zero-shot performance on multiple VQA benchmarks. Our experiments illustrate FlexCap's utility for tasks including image labeling, object attribute recognition, and visual dialog. Project webpage: https://flex-cap.github.io .
The internal workings of modern deep learning models stay often unclear to an external observer, although spatial attention mechanisms are involved. The idea of this work is to translate these spatial attentions into natural language to provide a simpler access to the model's function. Thus, I took a neural image captioning model and measured the reactions to external modification in its spatial attention for three different interface methods: a fixation over the whole generation process, a fixation for the first time-steps and an addition to the generator's attention. The experimental results for bounding box based spatial attention vectors have shown that the captioning model reacts to method dependent changes in up to 52.65% and includes in 9.00% of the cases object categories, which were otherwise unmentioned. Afterwards, I established such a link to a hierarchical co-attention network for visual question answering by extraction of its word, phrase and question level spatial attentions. Here, generated captions for the word level included details of the question-answer pairs in up to 55.20% of the cases. This work indicates that spatial attention seen as an external interface for image caption generators is an useful method to access visual functions in natural language.
Visual reasoning, as a prominent research area, plays a crucial role in AI by facilitating concept formation and interaction with the world. However, current works are usually carried out separately on small datasets thus lacking generalization ability. Through rigorous evaluation of diverse benchmarks, we demonstrate the shortcomings of existing ad-hoc methods in achieving cross-domain reasoning and their tendency to data bias fitting. In this paper, we revisit visual reasoning with a two-stage perspective: (1) symbolization and (2) logical reasoning given symbols or their representations. We find that the reasoning stage is better at generalization than symbolization. Thus, it is more efficient to implement symbolization via separated encoders for different data domains while using a shared reasoner. Given our findings, we establish design principles for visual reasoning frameworks following the separated symbolization and shared reasoning. The proposed two-stage framework achieves impressive generalization ability on various visual reasoning tasks, including puzzles, physical prediction, and visual question answering (VQA), encompassing both 2D and 3D modalities. We believe our insights will pave the way for generalizable visual reasoning.
In this paper, we present our solutions for a spectrum of automation tasks in life-saving intervention procedures within the Trauma THOMPSON (T3) Challenge, encompassing action recognition, action anticipation, and Visual Question Answering (VQA). For action recognition and anticipation, we propose a pre-processing strategy that samples and stitches multiple inputs into a single image and then incorporates momentum- and attention-based knowledge distillation to improve the performance of the two tasks. For training, we present an action dictionary-guided design, which consistently yields the most favorable results across our experiments. In the realm of VQA, we leverage object-level features and deploy co-attention networks to train both object and question features. Notably, we introduce a novel frame-question cross-attention mechanism at the network's core for enhanced performance. Our solutions achieve the $2^{nd}$ rank in action recognition and anticipation tasks and $1^{st}$ rank in the VQA task.
Document Visual Question Answering (DocVQA) is a practical yet challenging task, which is to ask questions based on documents while referring to multiple pages and different modalities of information, e.g, images and tables. To handle multi-modality, recent methods follow a similar Retrieval Augmented Generation (RAG) pipeline, but utilize Visual Language Models (VLMs) based embedding model to embed and retrieve relevant pages as images, and generate answers with VLMs that can accept an image as input. In this paper, we introduce SimpleDoc, a lightweight yet powerful retrieval - augmented framework for DocVQA. It boosts evidence page gathering by first retrieving candidates through embedding similarity and then filtering and re-ranking these candidates based on page summaries. A single VLM-based reasoner agent repeatedly invokes this dual-cue retriever, iteratively pulling fresh pages into a working memory until the question is confidently answered. SimpleDoc outperforms previous baselines by 3.2% on average on 4 DocVQA datasets with much fewer pages retrieved. Our code is available at https://github.com/ag2ai/SimpleDoc.
Recently, studies of visual question answering have explored various architectures of end-to-end networks and achieved promising results on both natural and synthetic datasets, which require explicitly compositional reasoning. However, it has been argued that these black-box approaches lack interpretability of results, and thus cannot perform well on generalization tasks due to overfitting the dataset bias. In this work, we aim to combine the benefits of both sides and overcome their limitations to achieve an end-to-end interpretable structural reasoning for general images without the requirement of layout annotations. Inspired by the property of a capsule network that can carve a tree structure inside a regular convolutional neural network (CNN), we propose a hierarchical compositional reasoning model called the "Linguistically driven Graph Capsule Network", where the compositional process is guided by the linguistic parse tree. Specifically, we bind each capsule in the lowest layer to bridge the linguistic embedding of a single word in the original question with visual evidence and then route them to the same capsule if they are siblings in the parse tree. This compositional process is achieved by performing inference on a linguistically driven conditional random field (CRF) and is performed across multiple graph capsule layers, which results in a compositional reasoning process inside a CNN. Experiments on the CLEVR dataset, CLEVR compositional generation test, and FigureQA dataset demonstrate the effectiveness and composition generalization ability of our end-to-end model.
In this report we present results of the ICDAR 2021 edition of the Document Visual Question Challenges. This edition complements the previous tasks on Single Document VQA and Document Collection VQA with a newly introduced on Infographics VQA. Infographics VQA is based on a new dataset of more than 5,000 infographics images and 30,000 question-answer pairs. The winner methods have scored 0.6120 ANLS in Infographics VQA task, 0.7743 ANLSL in Document Collection VQA task and 0.8705 ANLS in Single Document VQA. We present a summary of the datasets used for each task, description of each of the submitted methods and the results and analysis of their performance. A summary of the progress made on Single Document VQA since the first edition of the DocVQA 2020 challenge is also presented.
Video question answering (Video QA) presents a powerful testbed for human-like intelligent behaviors. The task demands new capabilities to integrate video processing, language understanding, binding abstract linguistic concepts to concrete visual artifacts, and deliberative reasoning over spacetime. Neural networks offer a promising approach to reach this potential through learning from examples rather than handcrafting features and rules. However, neural networks are predominantly feature-based - they map data to unstructured vectorial representation and thus can fall into the trap of exploiting shortcuts through surface statistics instead of true systematic reasoning seen in symbolic systems. To tackle this issue, we advocate for object-centric representation as a basis for constructing spatio-temporal structures from videos, essentially bridging the semantic gap between low-level pattern recognition and high-level symbolic algebra. To this end, we propose a new query-guided representation framework to turn a video into an evolving relational graph of objects, whose features and interactions are dynamically and conditionally inferred. The object lives are then summarized into resumes, lending naturally for deliberative relational reasoning that produces an answer to the query. The framework is evaluated on major Video QA datasets, demonstrating clear benefits of the object-centric approach to video reasoning.
Large vision and language assistants have enabled new capabilities for interpreting natural images. These approaches have recently been adapted to earth observation data, but they are only able to handle single image inputs, limiting their use for many real-world tasks. In this work, we develop a new vision and language assistant called TEOChat that can engage in conversations about temporal sequences of earth observation data. To train TEOChat, we curate an instruction-following dataset composed of many single image and temporal tasks including building change and damage assessment, semantic change detection, and temporal scene classification. We show that TEOChat can perform a wide variety of spatial and temporal reasoning tasks, substantially outperforming previous vision and language assistants, and even achieving comparable or better performance than several specialist models trained to perform specific tasks. Furthermore, TEOChat achieves impressive zero-shot performance on a change detection and change question answering dataset, outperforms GPT-4o and Gemini 1.5 Pro on multiple temporal tasks, and exhibits stronger single image capabilities than a comparable single image instruction-following model on scene classification, visual question answering, and captioning. We publicly release our data, model, and code at https://github.com/ermongroup/TEOChat .
Understanding audio-visual content and the ability to have an informative conversation about it have both been challenging areas for intelligent systems. The Audio Visual Scene-aware Dialog (AVSD) challenge, organized as a track of the Dialog System Technology Challenge 7 (DSTC7), proposes a combined task, where a system has to answer questions pertaining to a video given a dialogue with previous question-answer pairs and the video itself. We propose for this task a hierarchical encoder-decoder model which computes a multi-modal embedding of the dialogue context. It first embeds the dialogue history using two LSTMs. We extract video and audio frames at regular intervals and compute semantic features using pre-trained I3D and VGGish models, respectively. Before summarizing both modalities into fixed-length vectors using LSTMs, we use FiLM blocks to condition them on the embeddings of the current question, which allows us to reduce the dimensionality considerably. Finally, we use an LSTM decoder that we train with scheduled sampling and evaluate using beam search. Compared to the modality-fusing baseline model released by the AVSD challenge organizers, our model achieves a relative improvements of more than 16%, scoring 0.36 BLEU-4 and more than 33%, scoring 0.997 CIDEr.
Visual Grounding (VG) in Visual Question Answering (VQA) systems describes how well a system manages to tie a question and its answer to relevant image regions. Systems with strong VG are considered intuitively interpretable and suggest an improved scene understanding. While VQA accuracy performances have seen impressive gains over the past few years, explicit improvements to VG performance and evaluation thereof have often taken a back seat on the road to overall accuracy improvements. A cause of this originates in the predominant choice of learning paradigm for VQA systems, which consists of training a discriminative classifier over a predetermined set of answer options. In this work, we break with the dominant VQA modeling paradigm of classification and investigate VQA from the standpoint of an information retrieval task. As such, the developed system directly ties VG into its core search procedure. Our system operates over a weighted, directed, acyclic graph, a.k.a. "lattice", which is derived from the scene graph of a given image in conjunction with region-referring expressions extracted from the question. We give a detailed analysis of our approach and discuss its distinctive properties and limitations. Our approach achieves the strongest VG performance among examined systems and exhibits exceptional generalization capabilities in a number of scenarios.
장시간 비디오 질의응답은 답이 비디오 전반에 흩어진 소수의 결정적 순간에 좌우되는 경우가 많고, 메모리 제약으로 인해 멀티모달 대규모 언어 모델(MLLM)이 프레임을 극히 낮은 비율로 샘플링해야 하여 핵심 증거가 누락될 위험이 있는 희소성이 발생하기 때문에 어렵다. 컨텍스트 크기를 공격적으로 키우는 것은 직관적이지만, 성능은 편향, 즉 허위 언어적 상관관계와 두드러지지만 무관한 시각적 관찰에서 비롯되는 오도하는 단서에 의해 근본적으로 제약된다고 본 논문은 주장한다. 본 논문에서는 먼저 MLLM의 지름길 편향 행동을 체계적으로 진단하기 위해 설계된 벤치마크인 S-MME를 소개한다. 이러한 실패를 완화하기 위해 학습이 필요 없는 프레임워크인 반사실적 장시간 비디오 증거 인식 추론(CLEAR)을 추가로 제안한다. CLEAR는 전체 비디오-질문 쌍을 완전한 뷰로 간주하고, 질문만 유지하거나 지역적으로 두드러진 시각 클립만 유지한 증강 뷰를 통해 편향 효과를 추정한다. 이후 추론 시 은닉 상태에 개입하여 불일치를 완화함으로써 정답을 확신 있게 예측할 수 있게 한다. 5개 벤치마크에 대한 실험 연구를 통해 본 방법이 일반화 가능하며 다양한 MLLM에 통합될 수 있고, 예측과 강건성에서 일관된 향상을 가져옴을 보인다. CLEAR가 장시간 비디오 이해를 위한 테스트 시점 확장에서 상보적인 방향을 제시하기를 기대한다.
Prior work in visual dialog has focused on training deep neural models on VisDial in isolation. Instead, we present an approach to leverage pretraining on related vision-language datasets before transferring to visual dialog. We adapt the recently proposed ViLBERT (Lu et al., 2019) model for multi-turn visually-grounded conversations. Our model is pretrained on the Conceptual Captions and Visual Question Answering datasets, and finetuned on VisDial. Our best single model outperforms prior published work (including model ensembles) by more than 1% absolute on NDCG and MRR. Next, we find that additional finetuning using "dense" annotations in VisDial leads to even higher NDCG -- more than 10% over our base model -- but hurts MRR -- more than 17% below our base model! This highlights a trade-off between the two primary metrics -- NDCG and MRR -- which we find is due to dense annotations not correlating well with the original ground-truth answers to questions.
Recent Audio-Visual Question Answering (AVQA) methods rely on complete visual and audio input to answer questions accurately. However, in real-world scenarios, issues such as device malfunctions and data transmission errors frequently result in missing audio or visual modality. In such cases, existing AVQA methods suffer significant performance degradation. In this paper, we propose a framework that ensures robust AVQA performance even when a modality is missing. First, we propose a Relation-aware Missing Modal (RMM) generator with Relation-aware Missing Modal Recalling (RMMR) loss to enhance the ability of the generator to recall missing modal information by understanding the relationships and context among the available modalities. Second, we design an Audio-Visual Relation-aware (AVR) diffusion model with Audio-Visual Enhancing (AVE) loss to further enhance audio-visual features by leveraging the relationships and shared cues between the audio-visual modalities. As a result, our method can provide accurate answers by effectively utilizing available information even when input modalities are missing. We believe our method holds potential applications not only in AVQA research but also in various multi-modal scenarios.
In the past year, Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance in tasks such as visual question answering, visual understanding and reasoning. However, the extensive model size and high training and inference costs have hindered the widespread application of MLLMs in academia and industry. Thus, studying efficient and lightweight MLLMs has enormous potential, especially in edge computing scenarios. In this survey, we provide a comprehensive and systematic review of the current state of efficient MLLMs. Specifically, we summarize the timeline of representative efficient MLLMs, research state of efficient structures and strategies, and the applications. Finally, we discuss the limitations of current efficient MLLM research and promising future directions. Please refer to our GitHub repository for more details: https://github.com/lijiannuist/Efficient-Multimodal-LLMs-Survey.
Vision-language models (VLMs) integrate visual and textual information, enabling a wide range of applications such as image captioning and visual question answering, making them crucial for modern AI systems. However, their high computational demands pose challenges for real-time applications. This has led to a growing focus on developing efficient vision language models. In this survey, we review key techniques for optimizing VLMs on edge and resource-constrained devices. We also explore compact VLM architectures, frameworks and provide detailed insights into the performance-memory trade-offs of efficient VLMs. Furthermore, we establish a GitHub repository at https://github.com/MPSCUMBC/Efficient-Vision-Language-Models-A-Survey to compile all surveyed papers, which we will actively update. Our objective is to foster deeper research in this area.
Large Vision-Language Models (LVLMs), despite their recent success, are hardly comprehensively tested for their cognitive abilities. Inspired by the prevalent use of the "Cookie Theft" task in human cognition test, we propose a novel evaluation benchmark to evaluate high-level cognitive ability of LVLMs using images with rich semantics. It defines eight reasoning capabilities and consists of an image description task and a visual question answering task. Our evaluation on well-known LVLMs shows that there is still a large gap in cognitive ability between LVLMs and humans.
Modern VLMs have achieved near-saturation accuracy in English document visual question-answering (VQA). However, this task remains challenging in lower resource languages due to a dearth of suitable training and evaluation data. In this paper we present scalable methods for curating such datasets by focusing on Hungarian, approximately the 17th highest resource language on the internet. Specifically, we present HuDocVQA and HuDocVQA-manual, document VQA datasets that modern VLMs significantly underperform on compared to English DocVQA. HuDocVQA-manual is a small manually curated dataset based on Hungarian documents from Common Crawl, while HuDocVQA is a larger synthetically generated VQA data set from the same source. We apply multiple rounds of quality filtering and deduplication to HuDocVQA in order to match human-level quality in this dataset. We also present HuCCPDF, a dataset of 117k pages from Hungarian Common Crawl PDFs along with their transcriptions, which can be used for training a model for Hungarian OCR. To validate the quality of our datasets, we show how finetuning on a mixture of these datasets can improve accuracy on HuDocVQA for Llama 3.2 11B Instruct by +7.2%. Our datasets and code will be released to the public to foster further research in multilingual DocVQA.
Visual Question Answering systems target answering open-ended textual questions given input images. They are a testbed for learning high-level reasoning with a primary use in HCI, for instance assistance for the visually impaired. Recent research has shown that state-of-the-art models tend to produce answers exploiting biases and shortcuts in the training data, and sometimes do not even look at the input image, instead of performing the required reasoning steps. We present VisQA, a visual analytics tool that explores this question of reasoning vs. bias exploitation. It exposes the key element of state-of-the-art neural models -- attention maps in transformers. Our working hypothesis is that reasoning steps leading to model predictions are observable from attention distributions, which are particularly useful for visualization. The design process of VisQA was motivated by well-known bias examples from the fields of deep learning and vision-language reasoning and evaluated in two ways. First, as a result of a collaboration of three fields, machine learning, vision and language reasoning, and data analytics, the work lead to a better understanding of bias exploitation of neural models for VQA, which eventually resulted in an impact on its design and training through the proposition of a method for the transfer of reasoning patterns from an oracle model. Second, we also report on the design of VisQA, and a goal-oriented evaluation of VisQA targeting the analysis of a model decision process from multiple experts, providing evidence that it makes the inner workings of models accessible to users.
Visual commonsense contains knowledge about object properties, relationships, and behaviors in visual data. Discovering visual commonsense can provide a more comprehensive and richer understanding of images, and enhance the reasoning and decision-making capabilities of computer vision systems. However, the visual commonsense defined in existing visual commonsense discovery studies is coarse-grained and incomplete. In this work, we draw inspiration from a commonsense knowledge base ConceptNet in natural language processing, and systematically define the types of visual commonsense. Based on this, we introduce a new task, Visual Commonsense Discovery (VCD), aiming to extract fine-grained commonsense of different types contained within different objects in the image. We accordingly construct a dataset (VCDD) from Visual Genome and ConceptNet for VCD, featuring over 100,000 images and 14 million object-commonsense pairs. We furthermore propose a generative model (VCDM) that integrates a vision-language model with instruction tuning to tackle VCD. Automatic and human evaluations demonstrate VCDM's proficiency in VCD, particularly outperforming GPT-4V in implicit commonsense discovery. The value of VCD is further demonstrated by its application to two downstream tasks, including visual commonsense evaluation and visual question answering. The data and code will be made available on GitHub.