Luowei Zhou

Zhenhailong Wang, Manling Li, Ruochen Xu et al.

The goal of this work is to build flexible video-language models that can generalize to various video-to-text tasks from few examples, such as domain-specific captioning, question answering, and future event prediction. Existing few-shot video-language learners focus exclusively on the encoder, resulting in the absence of a video-to-text decoder to handle generative tasks. Video captioners have been pretrained on large-scale video-language datasets, but they rely heavily on finetuning and lack the ability to generate text for unseen tasks in a few-shot setting. We propose VidIL, a few-shot Video-language Learner via Image and Language models, which demonstrates strong performance on few-shot video-to-text tasks without the necessity of pretraining or finetuning on any video datasets. We use the image-language models to translate the video content into frame captions, object, attribute, and event phrases, and compose them into a temporal structure template. We then instruct a language model, with a prompt containing a few in-context examples, to generate a target output from the composed content. The flexibility of prompting allows the model to capture any form of text input, such as automatic speech recognition (ASR) transcripts. Our experiments demonstrate the power of language models in understanding videos on a wide variety of video-language tasks, including video captioning, video question answering, video caption retrieval, and video future event prediction. Especially, on video future event prediction, our few-shot model significantly outperforms state-of-the-art supervised models trained on large-scale video datasets. Code and resources are publicly available for research purposes at https://github.com/MikeWangWZHL/VidIL .

Zhecan Wang, Noel Codella, Yen-Chun Chen et al. · microsoft-research

Cross-modal encoders for vision-language (VL) tasks are often pretrained with carefully curated vision-language datasets. While these datasets reach an order of 10 million samples, the labor cost is prohibitive to scale further. Conversely, unimodal encoders are pretrained with simpler annotations that are less cost-prohibitive, achieving scales of hundreds of millions to billions. As a result, unimodal encoders have achieved state-of-art (SOTA) on many downstream tasks. However, challenges remain when applying to VL tasks. The pretraining data is not optimal for cross-modal architectures and requires heavy computational resources. In addition, unimodal architectures lack cross-modal interactions that have demonstrated significant benefits for VL tasks. Therefore, how to best leverage pretrained unimodal encoders for VL tasks is still an area of active research. In this work, we propose a method to leverage unimodal vision and text encoders for VL tasks that augment existing VL approaches while conserving computational complexity. Specifically, we propose Multimodal Adaptive Distillation (MAD), which adaptively distills useful knowledge from pretrained encoders to cross-modal VL encoders. Second, to better capture nuanced impacts on VL task performance, we introduce an evaluation protocol that includes Visual Commonsense Reasoning (VCR), Visual Entailment (SNLI-VE), and Visual Question Answering (VQA), across a variety of data constraints and conditions of domain shift. Experiments demonstrate that MAD leads to consistent gains in the low-shot, domain-shifted, and fully-supervised conditions on VCR, SNLI-VE, and VQA, achieving SOTA performance on VCR compared to other single models pretrained with image-text data. Finally, MAD outperforms concurrent works utilizing pretrained vision encoder from CLIP. Code will be made available.

Haoxuan You, Luowei Zhou, Bin Xiao et al.

Large-scale multi-modal contrastive pre-training has demonstrated great utility to learn transferable features for a range of downstream tasks by mapping multiple modalities into a shared embedding space. Typically, this has employed separate encoders for each modality. However, recent work suggests that transformers can support learning across multiple modalities and allow knowledge sharing. Inspired by this, we investigate a variety of Modality-Shared Contrastive Language-Image Pre-training (MS-CLIP) frameworks. More specifically, we question how many parameters of a transformer model can be shared across modalities during contrastive pre-training, and rigorously examine architectural design choices that position the proportion of parameters shared along a spectrum. In studied conditions, we observe that a mostly unified encoder for vision and language signals outperforms all other variations that separate more parameters. Additionally, we find that light-weight modality-specific parallel modules further improve performance. Experimental results show that the proposed MS-CLIP approach outperforms vanilla CLIP by up to 13\% relative in zero-shot ImageNet classification (pre-trained on YFCC-100M), while simultaneously supporting a reduction of parameters. In addition, our approach outperforms vanilla CLIP by 1.6 points in linear probing on a collection of 24 downstream vision tasks. Furthermore, we discover that sharing parameters leads to semantic concepts from different modalities being encoded more closely in the embedding space, facilitating the transferring of common semantic structure (e.g., attention patterns) from language to vision. Code is available at \href{https://github.com/Hxyou/MSCLIP}{URL}.

Junke Wang, Dongdong Chen, Zuxuan Wu et al.

This paper presents OmniVL, a new foundation model to support both image-language and video-language tasks using one universal architecture. It adopts a unified transformer-based visual encoder for both image and video inputs, and thus can perform joint image-language and video-language pretraining. We demonstrate, for the first time, such a paradigm benefits both image and video tasks, as opposed to the conventional one-directional transfer (e.g., use image-language to help video-language). To this end, we propose a decoupled joint pretraining of image-language and video-language to effectively decompose the vision-language modeling into spatial and temporal dimensions and obtain performance boost on both image and video tasks. Moreover, we introduce a novel unified vision-language contrastive (UniVLC) loss to leverage image-text, video-text, image-label (e.g., image classification), video-label (e.g., video action recognition) data together, so that both supervised and noisily supervised pretraining data are utilized as much as possible. Without incurring extra task-specific adaptors, OmniVL can simultaneously support visual only tasks (e.g., image classification, video action recognition), cross-modal alignment tasks (e.g., image/video-text retrieval), and multi-modal understanding and generation tasks (e.g., image/video question answering, captioning). We evaluate OmniVL on a wide range of downstream tasks and achieve state-of-the-art or competitive results with similar model size and data scale.

Difei Gao, Luowei Zhou, Lei Ji et al.

To build Video Question Answering (VideoQA) systems capable of assisting humans in daily activities, seeking answers from long-form videos with diverse and complex events is a must. Existing multi-modal VQA models achieve promising performance on images or short video clips, especially with the recent success of large-scale multi-modal pre-training. However, when extending these methods to long-form videos, new challenges arise. On the one hand, using a dense video sampling strategy is computationally prohibitive. On the other hand, methods relying on sparse sampling struggle in scenarios where multi-event and multi-granularity visual reasoning are required. In this work, we introduce a new model named Multi-modal Iterative Spatial-temporal Transformer (MIST) to better adapt pre-trained models for long-form VideoQA. Specifically, MIST decomposes traditional dense spatial-temporal self-attention into cascaded segment and region selection modules that adaptively select frames and image regions that are closely relevant to the question itself. Visual concepts at different granularities are then processed efficiently through an attention module. In addition, MIST iteratively conducts selection and attention over multiple layers to support reasoning over multiple events. The experimental results on four VideoQA datasets, including AGQA, NExT-QA, STAR, and Env-QA, show that MIST achieves state-of-the-art performance and is superior at computation efficiency and interpretability.

Weicheng Kuo, AJ Piergiovanni, Dahun Kim et al.

The development of language models have moved from encoder-decoder to decoder-only designs. In addition, we observe that the two most popular multimodal tasks, the generative and contrastive tasks, are nontrivial to accommodate in one architecture, and further need adaptations for downstream tasks. We propose a novel paradigm of training with a decoder-only model for multimodal tasks, which is surprisingly effective in jointly learning of these disparate vision-language tasks. This is done with a simple model, called MaMMUT. It consists of a single vision encoder and a text decoder, and is able to accommodate contrastive and generative learning by a novel two-pass approach on the text decoder. We demonstrate that joint learning of these diverse objectives is simple, effective, and maximizes the weight-sharing of the model across these tasks. Furthermore, the same architecture enables straightforward extensions to open-vocabulary object detection and video-language tasks. The model tackles a diverse range of tasks, while being modest in capacity. Our model achieves the state of the art on image-text and text-image retrieval, video question answering and open-vocabulary detection tasks, outperforming much larger and more extensively trained foundational models. It shows very competitive results on VQA and Video Captioning, especially considering its capacity. Ablations confirm the flexibility and advantages of our approach.

Yujia Xie, Luowei Zhou, Xiyang Dai et al.

People say, "A picture is worth a thousand words". Then how can we get the rich information out of the image? We argue that by using visual clues to bridge large pretrained vision foundation models and language models, we can do so without any extra cross-modal training. Thanks to the strong zero-shot capability of foundation models, we start by constructing a rich semantic representation of the image (e.g., image tags, object attributes / locations, captions) as a structured textual prompt, called visual clues, using a vision foundation model. Based on visual clues, we use large language model to produce a series of comprehensive descriptions for the visual content, which is then verified by the vision model again to select the candidate that aligns best with the image. We evaluate the quality of generated descriptions by quantitative and qualitative measurement. The results demonstrate the effectiveness of such a structured semantic representation.

Rui Wang, Zuxuan Wu, Dongdong Chen et al.

Transformer-based models have achieved top performance on major video recognition benchmarks. Benefiting from the self-attention mechanism, these models show stronger ability of modeling long-range dependencies compared to CNN-based models. However, significant computation overheads, resulted from the quadratic complexity of self-attention on top of a tremendous number of tokens, limit the use of existing video transformers in applications with limited resources like mobile devices. In this paper, we extend Mobile-Former to Video Mobile-Former, which decouples the video architecture into a lightweight 3D-CNNs for local context modeling and a Transformer modules for global interaction modeling in a parallel fashion. To avoid significant computational cost incurred by computing self-attention between the large number of local patches in videos, we propose to use very few global tokens (e.g., 6) for a whole video in Transformers to exchange information with 3D-CNNs with a cross-attention mechanism. Through efficient global spatial-temporal modeling, Video Mobile-Former significantly improves the video recognition performance of alternative lightweight baselines, and outperforms other efficient CNN-based models at the low FLOP regime from 500M to 6G total FLOPs on various video recognition tasks. It is worth noting that Video Mobile-Former is the first Transformer-based video model which constrains the computational budget within 1G FLOPs.

Difei Gao, Lei Ji, Luowei Zhou et al.

Recent research on Large Language Models (LLMs) has led to remarkable advancements in general NLP AI assistants. Some studies have further explored the use of LLMs for planning and invoking models or APIs to address more general multi-modal user queries. Despite this progress, complex visual-based tasks still remain challenging due to the diverse nature of visual tasks. This diversity is reflected in two aspects: 1) Reasoning paths. For many real-life applications, it is hard to accurately decompose a query simply by examining the query itself. Planning based on the specific visual content and the results of each step is usually required. 2) Flexible inputs and intermediate results. Input forms could be flexible for in-the-wild cases, and involves not only a single image or video but a mixture of videos and images, e.g., a user-view image with some reference videos. Besides, a complex reasoning process will also generate diverse multimodal intermediate results, e.g., video narrations, segmented video clips, etc. To address such general cases, we propose a multi-modal AI assistant, AssistGPT, with an interleaved code and language reasoning approach called Plan, Execute, Inspect, and Learn (PEIL) to integrate LLMs with various tools. Specifically, the Planner is capable of using natural language to plan which tool in Executor should do next based on the current reasoning progress. Inspector is an efficient memory manager to assist the Planner to feed proper visual information into a specific tool. Finally, since the entire reasoning process is complex and flexible, a Learner is designed to enable the model to autonomously explore and discover the optimal solution. We conducted experiments on A-OKVQA and NExT-QA benchmarks, achieving state-of-the-art results. Moreover, showcases demonstrate the ability of our system to handle questions far more complex than those found in the benchmarks.

Weitai Kang, Luowei Zhou, Junyi Wu et al.

Unlike Object Detection, Visual Grounding task necessitates the detection of an object described by complex free-form language. To simultaneously model such complex semantic and visual representations, recent state-of-the-art studies adopt transformer-based models to fuse features from both modalities, further introducing various modules that modulate visual features to align with the language expressions and eliminate the irrelevant redundant information. However, their loss function, still adopting common Object Detection losses, solely governs the bounding box regression output, failing to fully optimize for the above objectives. To tackle this problem, in this paper, we first analyze the attention mechanisms of transformer-based models. Building upon this, we further propose a novel framework named Attention-Driven Constraint Balancing (AttBalance) to optimize the behavior of visual features within language-relevant regions. Extensive experimental results show that our method brings impressive improvements. Specifically, we achieve constant improvements over five different models evaluated on four different benchmarks. Moreover, we attain a new state-of-the-art performance by integrating our method into QRNet.

Gheorghe Comanici, Eric Bieber, Mike Schaekermann et al. · amazon-science, baidu

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. Gemini 2.5 Flash provides excellent reasoning abilities at a fraction of the compute and latency requirements and Gemini 2.0 Flash and Flash-Lite provide high performance at low latency and cost. Taken together, the Gemini 2.X model generation spans the full Pareto frontier of model capability vs cost, allowing users to explore the boundaries of what is possible with complex agentic problem solving.

Deen Dayal Mohan, Hossein Souri, Vitali Petsiuk et al.

Until recently, the success of large-scale vision-language models (VLMs) has primarily relied on billion-sample datasets, posing a significant barrier to progress. Latest works have begun to close this gap by improving supervision quality, but each addresses only a subset of the weaknesses in contrastive pretraining. We present GoldiCLIP, a framework built on a Goldilocks principle of finding the right balance of supervision signals. Our multifaceted training framework synergistically combines three key innovations: (1) a text-conditioned self-distillation method to align both text-agnostic and text-conditioned features; (2) an encoder integrated decoder with Visual Question Answering (VQA) objective that enables the encoder to generalize beyond the caption-like queries; and (3) an uncertainty-based weighting mechanism that automatically balances all heterogeneous losses. Trained on just 30 million images, 300x less data than leading methods, GoldiCLIP achieves state-of-the-art among data-efficient approaches, improving over the best comparable baseline by 2.2 points on MSCOCO retrieval, 2.0 on fine-grained retrieval, and 5.9 on question-based retrieval, while remaining competitive with billion-scale models. Project page: https://petsi.uk/goldiclip.

Sherry X. Chen, Yi Wei, Luowei Zhou et al.

Recent advances in instruction-guided image editing underscore the need for effective automated evaluation. While Vision-Language Models (VLMs) have been explored as judges, open-source models struggle with alignment, and proprietary models lack transparency and cost efficiency. Additionally, no public training datasets exist to fine-tune open-source VLMs, only small benchmarks with diverse evaluation schemes. To address this, we introduce ADIEE, an automated dataset creation approach which is then used to train a scoring model for instruction-guided image editing evaluation. We generate a large-scale dataset with over 100K samples and use it to fine-tune a LLaVA-NeXT-8B model modified to decode a numeric score from a custom token. The resulting scorer outperforms all open-source VLMs and Gemini-Pro 1.5 across all benchmarks, achieving a 0.0696 (+17.24%) gain in score correlation with human ratings on AURORA-Bench, and improving pair-wise comparison accuracy by 4.03% (+7.21%) on GenAI-Bench and 4.75% (+9.35%) on AURORA-Bench, respectively, compared to the state-of-the-art. The scorer can act as a reward model, enabling automated best edit selection and model fine-tuning. Notably, the proposed scorer can boost MagicBrush model's average evaluation score on ImagenHub from 5.90 to 6.43 (+8.98%). Our code and models are available at https://github.com/SherryXTChen/ADIEE.git.

Yiwu Zhong, Jianwei Yang, Pengchuan Zhang et al.

Contrastive language-image pretraining (CLIP) using image-text pairs has achieved impressive results on image classification in both zero-shot and transfer learning settings. However, we show that directly applying such models to recognize image regions for object detection leads to poor performance due to a domain shift: CLIP was trained to match an image as a whole to a text description, without capturing the fine-grained alignment between image regions and text spans. To mitigate this issue, we propose a new method called RegionCLIP that significantly extends CLIP to learn region-level visual representations, thus enabling fine-grained alignment between image regions and textual concepts. Our method leverages a CLIP model to match image regions with template captions and then pretrains our model to align these region-text pairs in the feature space. When transferring our pretrained model to the open-vocabulary object detection tasks, our method significantly outperforms the state of the art by 3.8 AP50 and 2.2 AP for novel categories on COCO and LVIS datasets, respectively. Moreoever, the learned region representations support zero-shot inference for object detection, showing promising results on both COCO and LVIS datasets. Our code is available at https://github.com/microsoft/RegionCLIP.

Rui Wang, Dongdong Chen, Zuxuan Wu et al.

This paper studies the BERT pretraining of video transformers. It is a straightforward but worth-studying extension given the recent success from BERT pretraining of image transformers. We introduce BEVT which decouples video representation learning into spatial representation learning and temporal dynamics learning. In particular, BEVT first performs masked image modeling on image data, and then conducts masked image modeling jointly with masked video modeling on video data. This design is motivated by two observations: 1) transformers learned on image datasets provide decent spatial priors that can ease the learning of video transformers, which are often times computationally-intensive if trained from scratch; 2) discriminative clues, i.e., spatial and temporal information, needed to make correct predictions vary among different videos due to large intra-class and inter-class variations. We conduct extensive experiments on three challenging video benchmarks where BEVT achieves very promising results. On Kinetics 400, for which recognition mostly relies on discriminative spatial representations, BEVT achieves comparable results to strong supervised baselines. On Something-Something-V2 and Diving 48, which contain videos relying on temporal dynamics, BEVT outperforms by clear margins all alternative baselines and achieves state-of-the-art performance with a 71.4\% and 87.2\% Top-1 accuracy respectively. Code will be made available at \url{https://github.com/xyzforever/BEVT}.

Jie Lei, Linjie Li, Luowei Zhou et al.

The canonical approach to video-and-language learning (e.g., video question answering) dictates a neural model to learn from offline-extracted dense video features from vision models and text features from language models. These feature extractors are trained independently and usually on tasks different from the target domains, rendering these fixed features sub-optimal for downstream tasks. Moreover, due to the high computational overload of dense video features, it is often difficult (or infeasible) to plug feature extractors directly into existing approaches for easy finetuning. To provide a remedy to this dilemma, we propose a generic framework ClipBERT that enables affordable end-to-end learning for video-and-language tasks, by employing sparse sampling, where only a single or a few sparsely sampled short clips from a video are used at each training step. Experiments on text-to-video retrieval and video question answering on six datasets demonstrate that ClipBERT outperforms (or is on par with) existing methods that exploit full-length videos, suggesting that end-to-end learning with just a few sparsely sampled clips is often more accurate than using densely extracted offline features from full-length videos, proving the proverbial less-is-more principle. Videos in the datasets are from considerably different domains and lengths, ranging from 3-second generic domain GIF videos to 180-second YouTube human activity videos, showing the generalization ability of our approach. Comprehensive ablation studies and thorough analyses are provided to dissect what factors lead to this success. Our code is publicly available at https://github.com/jayleicn/ClipBERT

Luowei Zhou, Hamid Palangi, Lei Zhang et al.

This paper presents a unified Vision-Language Pre-training (VLP) model. The model is unified in that (1) it can be fine-tuned for either vision-language generation (e.g., image captioning) or understanding (e.g., visual question answering) tasks, and (2) it uses a shared multi-layer transformer network for both encoding and decoding, which differs from many existing methods where the encoder and decoder are implemented using separate models. The unified VLP model is pre-trained on a large amount of image-text pairs using the unsupervised learning objectives of two tasks: bidirectional and sequence-to-sequence (seq2seq) masked vision-language prediction. The two tasks differ solely in what context the prediction conditions on. This is controlled by utilizing specific self-attention masks for the shared transformer network. To the best of our knowledge, VLP is the first reported model that achieves state-of-the-art results on both vision-language generation and understanding tasks, as disparate as image captioning and visual question answering, across three challenging benchmark datasets: COCO Captions, Flickr30k Captions, and VQA 2.0. The code and the pre-trained models are available at https://github.com/LuoweiZhou/VLP.

Difei Gao, Lei Ji, Zechen Bai et al.

Graphical User Interface (GUI) automation holds significant promise for assisting users with complex tasks, thereby boosting human productivity. Existing works leveraging Large Language Model (LLM) or LLM-based AI agents have shown capabilities in automating tasks on Android and Web platforms. However, these tasks are primarily aimed at simple device usage and entertainment operations. This paper presents a novel benchmark, AssistGUI, to evaluate whether models are capable of manipulating the mouse and keyboard on the Windows platform in response to user-requested tasks. We carefully collected a set of 100 tasks from nine widely-used software applications, such as, After Effects and MS Word, each accompanied by the necessary project files for better evaluation. Moreover, we propose an advanced Actor-Critic Embodied Agent framework, which incorporates a sophisticated GUI parser driven by an LLM-agent and an enhanced reasoning mechanism adept at handling lengthy procedural tasks. Our experimental results reveal that our GUI Parser and Reasoning mechanism outshine existing methods in performance. Nevertheless, the potential remains substantial, with the best model attaining only a 46% success rate on our benchmark. We conclude with a thorough analysis of the current methods' limitations, setting the stage for future breakthroughs in this domain.

Sagar Shrestha, Gopal Sharma, Luowei Zhou et al.

Personalizing text-to-image diffusion models has traditionally relied on subject-specific fine-tuning approaches such as DreamBooth~\cite{ruiz2023dreambooth}, which are computationally expensive and slow at inference. Recent adapter- and encoder-based methods attempt to reduce this overhead but still depend on additional fine-tuning or large backbone models for satisfactory results. In this work, we revisit an orthogonal direction: fine-tuning-free personalization via Hypernetworks that predict LoRA-adapted weights directly from subject images. Prior hypernetwork-based approaches, however, suffer from costly data generation or unstable attempts to mimic base model optimization trajectories. We address these limitations with an end-to-end training objective, stabilized by a simple output regularization, yielding reliable and effective hypernetworks. Our method removes the need for per-subject optimization at test time while preserving both subject fidelity and prompt alignment. To further enhance compositional generalization at inference time, we introduce Hybrid-Model Classifier-Free Guidance (HM-CFG), which combines the compositional strengths of the base diffusion model with the subject fidelity of personalized models during sampling. Extensive experiments on CelebA-HQ, AFHQ-v2, and DreamBench demonstrate that our approach achieves strong personalization performance and highlights the promise of hypernetworks as a scalable and effective direction for open-category personalization.

Gemini Team, Rohan Anil, Sebastian Borgeaud et al.

This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consists of Ultra, Pro, and Nano sizes, suitable for applications ranging from complex reasoning tasks to on-device memory-constrained use-cases. Evaluation on a broad range of benchmarks shows that our most-capable Gemini Ultra model advances the state of the art in 30 of 32 of these benchmarks - notably being the first model to achieve human-expert performance on the well-studied exam benchmark MMLU, and improving the state of the art in every one of the 20 multimodal benchmarks we examined. We believe that the new capabilities of the Gemini family in cross-modal reasoning and language understanding will enable a wide variety of use cases. We discuss our approach toward post-training and deploying Gemini models responsibly to users through services including Gemini, Gemini Advanced, Google AI Studio, and Cloud Vertex AI.

Zhecan Wang, Noel Codella, Yen-Chun Chen et al.

Contrastive language-image pretraining (CLIP) links vision and language modalities into a unified embedding space, yielding the tremendous potential for vision-language (VL) tasks. While early concurrent works have begun to study this potential on a subset of tasks, important questions remain: 1) What is the benefit of CLIP on unstudied VL tasks? 2) Does CLIP provide benefit in low-shot or domain-shifted scenarios? 3) Can CLIP improve existing approaches without impacting inference or pretraining complexity? In this work, we seek to answer these questions through two key contributions. First, we introduce an evaluation protocol that includes Visual Commonsense Reasoning (VCR), Visual Entailment (SNLI-VE), and Visual Question Answering (VQA), across a variety of data availability constraints and conditions of domain shift. Second, we propose an approach, named CLIP Targeted Distillation (CLIP-TD), to intelligently distill knowledge from CLIP into existing architectures using a dynamically weighted objective applied to adaptively selected tokens per instance. Experiments demonstrate that our proposed CLIP-TD leads to exceptional gains in the low-shot (up to 51.9%) and domain-shifted (up to 71.3%) conditions of VCR, while simultaneously improving performance under standard fully-supervised conditions (up to 2%), achieving state-of-art performance on VCR compared to other single models that are pretrained with image-text data only. On SNLI-VE, CLIP-TD produces significant gains in low-shot conditions (up to 6.6%) as well as fully supervised (up to 3%). On VQA, CLIP-TD provides improvement in low-shot (up to 9%), and in fully-supervised (up to 1.3%). Finally, CLIP-TD outperforms concurrent works utilizing CLIP for finetuning, as well as baseline naive distillation approaches. Code will be made available.

Manling Li, Ruochen Xu, Shuohang Wang et al.

Vision-language (V+L) pretraining models have achieved great success in supporting multimedia applications by understanding the alignments between images and text. While existing vision-language pretraining models primarily focus on understanding objects in images or entities in text, they often ignore the alignment at the level of events and their argument structures. In this work, we propose a contrastive learning framework to enforce vision-language pretraining models to comprehend events and associated argument (participant) roles. To achieve this, we take advantage of text information extraction technologies to obtain event structural knowledge, and utilize multiple prompt functions to contrast difficult negative descriptions by manipulating event structures. We also design an event graph alignment loss based on optimal transport to capture event argument structures. In addition, we collect a large event-rich dataset (106,875 images) for pretraining, which provides a more challenging image retrieval benchmark to assess the understanding of complicated lengthy sentences. Experiments show that our zero-shot CLIP-Event outperforms the state-of-the-art supervised model in argument extraction on Multimedia Event Extraction, achieving more than 5% absolute F-score gain in event extraction, as well as significant improvements on a variety of downstream tasks under zero-shot settings.

Lu Yuan, Dongdong Chen, Yi-Ling Chen et al.

Automated visual understanding of our diverse and open world demands computer vision models to generalize well with minimal customization for specific tasks, similar to human vision. Computer vision foundation models, which are trained on diverse, large-scale dataset and can be adapted to a wide range of downstream tasks, are critical for this mission to solve real-world computer vision applications. While existing vision foundation models such as CLIP, ALIGN, and Wu Dao 2.0 focus mainly on mapping images and textual representations to a cross-modal shared representation, we introduce a new computer vision foundation model, Florence, to expand the representations from coarse (scene) to fine (object), from static (images) to dynamic (videos), and from RGB to multiple modalities (caption, depth). By incorporating universal visual-language representations from Web-scale image-text data, our Florence model can be easily adapted for various computer vision tasks, such as classification, retrieval, object detection, VQA, image caption, video retrieval and action recognition. Moreover, Florence demonstrates outstanding performance in many types of transfer learning: fully sampled fine-tuning, linear probing, few-shot transfer and zero-shot transfer for novel images and objects. All of these properties are critical for our vision foundation model to serve general purpose vision tasks. Florence achieves new state-of-the-art results in majority of 44 representative benchmarks, e.g., ImageNet-1K zero-shot classification with top-1 accuracy of 83.74 and the top-5 accuracy of 97.18, 62.4 mAP on COCO fine tuning, 80.36 on VQA, and 87.8 on Kinetics-600.

Linjie Li, Jie Lei, Zhe Gan et al.

Most existing video-and-language (VidL) research focuses on a single dataset, or multiple datasets of a single task. In reality, a truly useful VidL system is expected to be easily generalizable to diverse tasks, domains, and datasets. To facilitate the evaluation of such systems, we introduce Video-And-Language Understanding Evaluation (VALUE) benchmark, an assemblage of 11 VidL datasets over 3 popular tasks: (i) text-to-video retrieval; (ii) video question answering; and (iii) video captioning. VALUE benchmark aims to cover a broad range of video genres, video lengths, data volumes, and task difficulty levels. Rather than focusing on single-channel videos with visual information only, VALUE promotes models that leverage information from both video frames and their associated subtitles, as well as models that share knowledge across multiple tasks. We evaluate various baseline methods with and without large-scale VidL pre-training, and systematically investigate the impact of video input channels, fusion methods, and different video representations. We also study the transferability between tasks, and conduct multi-task learning under different settings. The significant gap between our best model and human performance calls for future study for advanced VidL models. VALUE is available at https://value-benchmark.github.io/.

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.

Luowei Zhou, Jingjing Liu, Yu Cheng et al.

This work concerns video-language pre-training and representation learning. In this now ubiquitous training scheme, a model first performs pre-training on paired videos and text (e.g., video clips and accompanied subtitles) from a large uncurated source corpus, before transferring to specific downstream tasks. This two-stage training process inevitably raises questions about the generalization ability of the pre-trained model, which is particularly pronounced when a salient domain gap exists between source and target data (e.g., instructional cooking videos vs. movies). In this paper, we first bring to light the sensitivity of pre-training objectives (contrastive vs. reconstructive) to domain discrepancy. Then, we propose a simple yet effective framework, CUPID, to bridge this domain gap by filtering and adapting source data to the target data, followed by domain-focused pre-training. Comprehensive experiments demonstrate that pre-training on a considerably small subset of domain-focused data can effectively close the source-target domain gap and achieve significant performance gain, compared to random sampling or even exploiting the full pre-training dataset. CUPID yields new state-of-the-art performance across multiple video-language and video tasks, including text-to-video retrieval [72, 37], video question answering [36], and video captioning [72], with consistent performance lift over different pre-training methods.

Nathan Louis, Luowei Zhou, Steven J. Yule et al.

Articulated hand pose tracking is an under-explored problem that carries the potential for use in an extensive number of applications, especially in the medical domain. With a robust and accurate tracking system on surgical videos, the motion dynamics and movement patterns of the hands can be captured and analyzed for many rich tasks. In this work, we propose a novel hand pose estimation model, CondPose, which improves detection and tracking accuracy by incorporating a pose prior into its prediction. We show improvements over state-of-the-art methods which provide frame-wise independent predictions, by following a temporally guided approach that effectively leverages past predictions. We collect Surgical Hands, the first dataset that provides multi-instance articulated hand pose annotations for videos. Our dataset provides over 8.1k annotated hand poses from publicly available surgical videos and bounding boxes, pose annotations, and tracking IDs to enable multi-instance tracking. When evaluated on Surgical Hands, we show our method outperforms the state-of-the-art approach using mean Average Precision (mAP), to measure pose estimation accuracy, and Multiple Object Tracking Accuracy (MOTA), to assess pose tracking performance. In comparison to a frame-wise independent strategy, we show greater performance in detecting and tracking hand poses and more substantial impact on localization accuracy. This has positive implications in generating more accurate representations of hands in the scene to be used for targeted downstream tasks.

Shuohang Wang, Luowei Zhou, Zhe Gan et al.

Transformer has become ubiquitous in the deep learning field. One of the key ingredients that destined its success is the self-attention mechanism, which allows fully-connected contextual encoding over input tokens. However, despite its effectiveness in modeling short sequences, self-attention suffers when handling inputs with extreme long-range dependencies, as its complexity grows quadratically with respect to the sequence length. Therefore, long sequences are often encoded by Transformer in chunks using a sliding window. In this paper, we propose Cluster-Former, a novel clustering-based sparse Transformer to perform attention across chunked sequences. The proposed framework is pivoted on two unique types of Transformer layer: Sliding-Window Layer and Cluster-Former Layer, which encode local sequence information and global context jointly and iteratively. This new design allows information integration beyond local windows, which is especially beneficial for question answering (QA) tasks that rely on long-range dependencies. Experiments show that Cluster-Former achieves state-of-the-art performance on several major QA benchmarks.

Luowei Zhou, Yannis Kalantidis, Xinlei Chen et al.

Video description is one of the most challenging problems in vision and language understanding due to the large variability both on the video and language side. Models, hence, typically shortcut the difficulty in recognition and generate plausible sentences that are based on priors but are not necessarily grounded in the video. In this work, we explicitly link the sentence to the evidence in the video by annotating each noun phrase in a sentence with the corresponding bounding box in one of the frames of a video. Our dataset, ActivityNet-Entities, augments the challenging ActivityNet Captions dataset with 158k bounding box annotations, each grounding a noun phrase. This allows training video description models with this data, and importantly, evaluate how grounded or "true" such model are to the video they describe. To generate grounded captions, we propose a novel video description model which is able to exploit these bounding box annotations. We demonstrate the effectiveness of our model on our dataset, but also show how it can be applied to image description on the Flickr30k Entities dataset. We achieve state-of-the-art performance on video description, video paragraph description, and image description and demonstrate our generated sentences are better grounded in the video.

Hao Huang, Luowei Zhou, Wei Zhang et al.

Video action recognition, a critical problem in video understanding, has been gaining increasing attention. To identify actions induced by complex object-object interactions, we need to consider not only spatial relations among objects in a single frame, but also temporal relations among different or the same objects across multiple frames. However, existing approaches that model video representations and non-local features are either incapable of explicitly modeling relations at the object-object level or unable to handle streaming videos. In this paper, we propose a novel dynamic hidden graph module to model complex object-object interactions in videos, of which two instantiations are considered: a visual graph that captures appearance/motion changes among objects and a location graph that captures relative spatiotemporal position changes among objects. Additionally, the proposed graph module allows us to process streaming videos, setting it apart from existing methods. Experimental results on benchmark datasets, Something-Something and ActivityNet, show the competitive performance of our method.

Luowei Zhou, Nathan Louis, Jason J. Corso

We study weakly-supervised video object grounding: given a video segment and a corresponding descriptive sentence, the goal is to localize objects that are mentioned from the sentence in the video. During training, no object bounding boxes are available, but the set of possible objects to be grounded is known beforehand. Existing approaches in the image domain use Multiple Instance Learning (MIL) to ground objects by enforcing matches between visual and semantic features. A naive extension of this approach to the video domain is to treat the entire segment as a bag of spatial object proposals. However, an object existing sparsely across multiple frames might not be detected completely since successfully spotting it from one single frame would trigger a satisfactory match. To this end, we propagate the weak supervisory signal from the segment level to frames that likely contain the target object. For frames that are unlikely to contain the target objects, we use an alternative penalty loss. We also leverage the interactions among objects as a textual guide for the grounding. We evaluate our model on the newly-collected benchmark YouCook2-BoundingBox and show improvements over competitive baselines.

Luowei Zhou, Yingbo Zhou, Jason J. Corso et al.

Dense video captioning aims to generate text descriptions for all events in an untrimmed video. This involves both detecting and describing events. Therefore, all previous methods on dense video captioning tackle this problem by building two models, i.e. an event proposal and a captioning model, for these two sub-problems. The models are either trained separately or in alternation. This prevents direct influence of the language description to the event proposal, which is important for generating accurate descriptions. To address this problem, we propose an end-to-end transformer model for dense video captioning. The encoder encodes the video into appropriate representations. The proposal decoder decodes from the encoding with different anchors to form video event proposals. The captioning decoder employs a masking network to restrict its attention to the proposal event over the encoding feature. This masking network converts the event proposal to a differentiable mask, which ensures the consistency between the proposal and captioning during training. In addition, our model employs a self-attention mechanism, which enables the use of efficient non-recurrent structure during encoding and leads to performance improvements. We demonstrate the effectiveness of this end-to-end model on ActivityNet Captions and YouCookII datasets, where we achieved 10.12 and 6.58 METEOR score, respectively.

Luowei Zhou, Chenliang Xu, Jason J. Corso

The potential for agents, whether embodied or software, to learn by observing other agents performing procedures involving objects and actions is rich. Current research on automatic procedure learning heavily relies on action labels or video subtitles, even during the evaluation phase, which makes them infeasible in real-world scenarios. This leads to our question: can the human-consensus structure of a procedure be learned from a large set of long, unconstrained videos (e.g., instructional videos from YouTube) with only visual evidence? To answer this question, we introduce the problem of procedure segmentation--to segment a video procedure into category-independent procedure segments. Given that no large-scale dataset is available for this problem, we collect a large-scale procedure segmentation dataset with procedure segments temporally localized and described; we use cooking videos and name the dataset YouCook2. We propose a segment-level recurrent network for generating procedure segments by modeling the dependencies across segments. The generated segments can be used as pre-processing for other tasks, such as dense video captioning and event parsing. We show in our experiments that the proposed model outperforms competitive baselines in procedure segmentation.

Luowei Zhou, Chenliang Xu, Parker Koch et al.

Attention mechanisms have attracted considerable interest in image captioning due to its powerful performance. However, existing methods use only visual content as attention and whether textual context can improve attention in image captioning remains unsolved. To explore this problem, we propose a novel attention mechanism, called \textit{text-conditional attention}, which allows the caption generator to focus on certain image features given previously generated text. To obtain text-related image features for our attention model, we adopt the guiding Long Short-Term Memory (gLSTM) captioning architecture with CNN fine-tuning. Our proposed method allows joint learning of the image embedding, text embedding, text-conditional attention and language model with one network architecture in an end-to-end manner. We perform extensive experiments on the MS-COCO dataset. The experimental results show that our method outperforms state-of-the-art captioning methods on various quantitative metrics as well as in human evaluation, which supports the use of our text-conditional attention in image captioning.

Luowei Zhou, Pei Yang, Chunlin Chen et al.

Reinforcement learning has significant applications for multi-agent systems, especially in unknown dynamic environments. However, most multi-agent reinforcement learning (MARL) algorithms suffer from such problems as exponential computation complexity in the joint state-action space, which makes it difficult to scale up to realistic multi-agent problems. In this paper, a novel algorithm named negotiation-based MARL with sparse interactions (NegoSI) is presented. In contrast to traditional sparse-interaction based MARL algorithms, NegoSI adopts the equilibrium concept and makes it possible for agents to select the non-strict Equilibrium Dominating Strategy Profile (non-strict EDSP) or Meta equilibrium for their joint actions. The presented NegoSI algorithm consists of four parts: the equilibrium-based framework for sparse interactions, the negotiation for the equilibrium set, the minimum variance method for selecting one joint action and the knowledge transfer of local Q-values. In this integrated algorithm, three techniques, i.e., unshared value functions, equilibrium solutions and sparse interactions are adopted to achieve privacy protection, better coordination and lower computational complexity, respectively. To evaluate the performance of the presented NegoSI algorithm, two groups of experiments are carried out regarding three criteria: steps of each episode (SEE), rewards of each episode (REE) and average runtime (AR). The first group of experiments is conducted using six grid world games and shows fast convergence and high scalability of the presented algorithm. Then in the second group of experiments NegoSI is applied to an intelligent warehouse problem and simulated results demonstrate the effectiveness of the presented NegoSI algorithm compared with other state-of-the-art MARL algorithms.