Hanoona Rasheed

Muhammad Maaz, Hanoona Rasheed, Salman Khan et al.

Conversation agents fueled by Large Language Models (LLMs) are providing a new way to interact with visual data. While there have been initial attempts for image-based conversation models, this work addresses the under-explored field of \emph{video-based conversation} by introducing Video-ChatGPT. It is a multimodal model that merges a video-adapted visual encoder with an LLM. The resulting model is capable of understanding and generating detailed conversations about videos. We introduce a new dataset of 100,000 video-instruction pairs used to train Video-ChatGPT acquired via manual and semi-automated pipeline that is easily scalable and robust to label noise. We also develop a quantitative evaluation framework for video-based dialogue models to objectively analyze the strengths and weaknesses of video-based dialogue models. Code: https://github.com/mbzuai-oryx/Video-ChatGPT.

Muhammad Uzair Khattak, Hanoona Rasheed, Muhammad Maaz et al.

Pre-trained vision-language (V-L) models such as CLIP have shown excellent generalization ability to downstream tasks. However, they are sensitive to the choice of input text prompts and require careful selection of prompt templates to perform well. Inspired by the Natural Language Processing (NLP) literature, recent CLIP adaptation approaches learn prompts as the textual inputs to fine-tune CLIP for downstream tasks. We note that using prompting to adapt representations in a single branch of CLIP (language or vision) is sub-optimal since it does not allow the flexibility to dynamically adjust both representation spaces on a downstream task. In this work, we propose Multi-modal Prompt Learning (MaPLe) for both vision and language branches to improve alignment between the vision and language representations. Our design promotes strong coupling between the vision-language prompts to ensure mutual synergy and discourages learning independent uni-modal solutions. Further, we learn separate prompts across different early stages to progressively model the stage-wise feature relationships to allow rich context learning. We evaluate the effectiveness of our approach on three representative tasks of generalization to novel classes, new target datasets and unseen domain shifts. Compared with the state-of-the-art method Co-CoOp, MaPLe exhibits favorable performance and achieves an absolute gain of 3.45% on novel classes and 2.72% on overall harmonic-mean, averaged over 11 diverse image recognition datasets. Our code and pre-trained models are available at https://github.com/muzairkhattak/multimodal-prompt-learning.

Abdelrahman Shaker, Muhammad Maaz, Hanoona Rasheed et al.

Owing to the success of transformer models, recent works study their applicability in 3D medical segmentation tasks. Within the transformer models, the self-attention mechanism is one of the main building blocks that strives to capture long-range dependencies. However, the self-attention operation has quadratic complexity which proves to be a computational bottleneck, especially in volumetric medical imaging, where the inputs are 3D with numerous slices. In this paper, we propose a 3D medical image segmentation approach, named UNETR++, that offers both high-quality segmentation masks as well as efficiency in terms of parameters, compute cost, and inference speed. The core of our design is the introduction of a novel efficient paired attention (EPA) block that efficiently learns spatial and channel-wise discriminative features using a pair of inter-dependent branches based on spatial and channel attention. Our spatial attention formulation is efficient having linear complexity with respect to the input sequence length. To enable communication between spatial and channel-focused branches, we share the weights of query and key mapping functions that provide a complimentary benefit (paired attention), while also reducing the overall network parameters. Our extensive evaluations on five benchmarks, Synapse, BTCV, ACDC, BRaTs, and Decathlon-Lung, reveal the effectiveness of our contributions in terms of both efficiency and accuracy. On Synapse, our UNETR++ sets a new state-of-the-art with a Dice Score of 87.2%, while being significantly efficient with a reduction of over 71% in terms of both parameters and FLOPs, compared to the best method in the literature. Code: https://github.com/Amshaker/unetr_plus_plus.

Hanoona Rasheed, Muhammad Uzair Khattak, Muhammad Maaz et al.

Large-scale multi-modal training with image-text pairs imparts strong generalization to CLIP model. Since training on a similar scale for videos is infeasible, recent approaches focus on the effective transfer of image-based CLIP to the video domain. In this pursuit, new parametric modules are added to learn temporal information and inter-frame relationships which require meticulous design efforts. Furthermore, when the resulting models are learned on videos, they tend to overfit on the given task distribution and lack in generalization aspect. This begs the following question: How to effectively transfer image-level CLIP representations to videos? In this work, we show that a simple Video Fine-tuned CLIP (ViFi-CLIP) baseline is generally sufficient to bridge the domain gap from images to videos. Our qualitative analysis illustrates that the frame-level processing from CLIP image-encoder followed by feature pooling and similarity matching with corresponding text embeddings helps in implicitly modeling the temporal cues within ViFi-CLIP. Such fine-tuning helps the model to focus on scene dynamics, moving objects and inter-object relationships. For low-data regimes where full fine-tuning is not viable, we propose a `bridge and prompt' approach that first uses fine-tuning to bridge the domain gap and then learns prompts on language and vision side to adapt CLIP representations. We extensively evaluate this simple yet strong baseline on zero-shot, base-to-novel generalization, few-shot and fully supervised settings across five video benchmarks. Our code is available at https://github.com/muzairkhattak/ViFi-CLIP.

Abdelrahman Shaker, Muhammad Maaz, Hanoona Rasheed et al.

Self-attention has become a defacto choice for capturing global context in various vision applications. However, its quadratic computational complexity with respect to image resolution limits its use in real-time applications, especially for deployment on resource-constrained mobile devices. Although hybrid approaches have been proposed to combine the advantages of convolutions and self-attention for a better speed-accuracy trade-off, the expensive matrix multiplication operations in self-attention remain a bottleneck. In this work, we introduce a novel efficient additive attention mechanism that effectively replaces the quadratic matrix multiplication operations with linear element-wise multiplications. Our design shows that the key-value interaction can be replaced with a linear layer without sacrificing any accuracy. Unlike previous state-of-the-art methods, our efficient formulation of self-attention enables its usage at all stages of the network. Using our proposed efficient additive attention, we build a series of models called "SwiftFormer" which achieves state-of-the-art performance in terms of both accuracy and mobile inference speed. Our small variant achieves 78.5% top-1 ImageNet-1K accuracy with only 0.8 ms latency on iPhone 14, which is more accurate and 2x faster compared to MobileViT-v2. Code: https://github.com/Amshaker/SwiftFormer

Hanoona Rasheed, Muhammad Maaz, Muhammad Uzair Khattak et al.

Existing open-vocabulary object detectors typically enlarge their vocabulary sizes by leveraging different forms of weak supervision. This helps generalize to novel objects at inference. Two popular forms of weak-supervision used in open-vocabulary detection (OVD) include pretrained CLIP model and image-level supervision. We note that both these modes of supervision are not optimally aligned for the detection task: CLIP is trained with image-text pairs and lacks precise localization of objects while the image-level supervision has been used with heuristics that do not accurately specify local object regions. In this work, we propose to address this problem by performing object-centric alignment of the language embeddings from the CLIP model. Furthermore, we visually ground the objects with only image-level supervision using a pseudo-labeling process that provides high-quality object proposals and helps expand the vocabulary during training. We establish a bridge between the above two object-alignment strategies via a novel weight transfer function that aggregates their complimentary strengths. In essence, the proposed model seeks to minimize the gap between object and image-centric representations in the OVD setting. On the COCO benchmark, our proposed approach achieves 36.6 AP50 on novel classes, an absolute 8.2 gain over the previous best performance. For LVIS, we surpass the state-of-the-art ViLD model by 5.0 mask AP for rare categories and 3.4 overall. Code: https://github.com/hanoonaR/object-centric-ovd.

Hanoona Rasheed, Muhammad Maaz, Sahal Shaji Mullappilly et al.

Large Multimodal Models (LMMs) extend Large Language Models to the vision domain. Initial LMMs used holistic images and text prompts to generate ungrounded textual responses. Recently, region-level LMMs have been used to generate visually grounded responses. However, they are limited to only referring to a single object category at a time, require users to specify the regions, or cannot offer dense pixel-wise object grounding. In this work, we present Grounding LMM (GLaMM), the first model that can generate natural language responses seamlessly intertwined with corresponding object segmentation masks. GLaMM not only grounds objects appearing in the conversations but is flexible enough to accept both textual and optional visual prompts (region of interest) as input. This empowers users to interact with the model at various levels of granularity, both in textual and visual domains. Due to the lack of standard benchmarks for the novel setting of visually Grounded Conversation Generation (GCG), we introduce a comprehensive evaluation protocol with our curated grounded conversations. Our proposed GCG task requires densely grounded concepts in natural scenes at a large-scale. To this end, we propose a densely annotated Grounding-anything Dataset (GranD) using our proposed automated annotation pipeline that encompasses 7.5M unique concepts grounded in a total of 810M regions available with segmentation masks. Besides GCG, GLaMM also performs effectively on several downstream tasks, e.g., referring expression segmentation, image and region-level captioning and vision-language conversations.

Daniel Bolya, Po-Yao Huang, Peize Sun et al. · meta-ai, mit

We introduce Perception Encoder (PE), a state-of-the-art vision encoder for image and video understanding trained via simple vision-language learning. Traditionally, vision encoders have relied on a variety of pretraining objectives, each tailored to specific downstream tasks such as classification, captioning, or localization. Surprisingly, after scaling our carefully tuned image pretraining recipe and refining with our robust video data engine, we find that contrastive vision-language training alone can produce strong, general embeddings for all of these downstream tasks. There is only one caveat: these embeddings are hidden within the intermediate layers of the network. To draw them out, we introduce two alignment methods: language alignment for multimodal language modeling, and spatial alignment for dense prediction. Together, our PE family of models achieves best-in-class results on a wide variety of tasks, including (1) zero-shot image and video classification and retrieval, simultaneously obtaining 86.6 average zero-shot ImageNet robustness and 76.9 zero-shot Kinetics-400 video classification; (2) document, image, and video Q&A, enabling 94.6 DocVQA, 80.9 InfographicVQA, and 82.7 PerceptionTest with an 8B LLM; and (3) spatial tasks such as detection, tracking, and depth estimation, setting a new COCO state-of-the-art of 66.0 box mAP. To foster further research, we release our models, code, and novel dataset of synthetically and human-annotated videos: https://github.com/facebookresearch/perception_models

Muhammad Maaz, Hanoona Rasheed, Abdelrahman Shaker et al.

In pursuit of more inclusive Vision-Language Models (VLMs), this study introduces a Large Multilingual Multimodal Model called PALO. PALO offers visual reasoning capabilities in 10 major languages, including English, Chinese, Hindi, Spanish, French, Arabic, Bengali, Russian, Urdu, and Japanese, that span a total of ~5B people (65% of the world population). Our approach involves a semi-automated translation approach to adapt the multimodal instruction dataset from English to the target languages using a fine-tuned Large Language Model, thereby ensuring high linguistic fidelity while allowing scalability due to minimal manual effort. The incorporation of diverse instruction sets helps us boost overall performance across multiple languages especially those that are underrepresented like Hindi, Arabic, Bengali, and Urdu. The resulting models are trained across three scales (1.7B, 7B and 13B parameters) to show the generalization and scalability where we observe substantial improvements compared to strong baselines. We also propose the first multilingual multimodal benchmark for the forthcoming approaches to evaluate their vision-language reasoning capabilities across languages. Code: https://github.com/mbzuai-oryx/PALO.

Jang Hyun Cho, Andrea Madotto, Effrosyni Mavroudi et al.

Vision-language models are integral to computer vision research, yet many high-performing models remain closed-source, obscuring their data, design and training recipe. The research community has responded by using distillation from black-box models to label training data, achieving strong benchmark results, at the cost of measurable scientific progress. However, without knowing the details of the teacher model and its data sources, scientific progress remains difficult to measure. In this paper, we study building a Perception Language Model (PLM) in a fully open and reproducible framework for transparent research in image and video understanding. We analyze standard training pipelines without distillation from proprietary models and explore large-scale synthetic data to identify critical data gaps, particularly in detailed video understanding. To bridge these gaps, we release 2.8M human-labeled instances of fine-grained video question-answer pairs and spatio-temporally grounded video captions. Additionally, we introduce PLM-VideoBench, a suite for evaluating challenging video understanding tasks focusing on the ability to reason about "what", "where", "when", and "how" of a video. We make our work fully reproducible by providing data, training recipes, code & models. https://github.com/facebookresearch/perception_models

Muhammad Maaz, Hanoona Rasheed, Fahad Shahbaz Khan et al.

Reasoning over dynamic visual content remains a central challenge for multimodal large language models. Recent thinking models generate explicit reasoning traces for interpretability; however, their reasoning often appears convincing while being logically inconsistent or weakly grounded in visual evidence. We identify and formalize these issues through two diagnostic metrics: Think Answer Consistency (TAC), which measures the alignment between reasoning and answers, and Video Attention Score (VAS), which captures the extent to which reasoning depends on visual versus textual cues. Analysis across 11 video reasoning benchmarks shows that current models rely heavily on linguistic priors rather than visual content. To address this, we propose a reinforcement learning approach that enhances both temporal precision and reasoning consistency. Our approach combines timestamp aware supervised fine tuning with Group Relative Policy Optimization (GRPO) guided by a novel Temporal Alignment Reward (TAR). This dual step post training stage encourages temporally aligned and causally coherent video reasoning. The resulting model, Video R2, achieves consistently higher TAC, VAS, and accuracy across multiple benchmarks, demonstrating that improvements in temporal alignment and reasoning coherence lead to more accurate and trustworthy video understanding. Code: https://github.com/mbzuai-oryx/Video-R2

Hanoona Rasheed, Mohammed Zumri, Muhammad Maaz et al.

Recent multimodal large language models (MLLMs) have advanced video understanding, yet most still "think about videos" ie once a video is encoded, reasoning unfolds entirely in text, treating visual input as a static context. This passive paradigm creates a semantic bottleneck: models cannot rewatch, refocus, or verify evidence, leading to shallow visual reasoning on tasks requiring fine grained spatio temporal understanding. In this work, we introduce Interactive Video Reasoning, a new paradigm that transforms video into an active cognitive workspace, enabling models to "think with videos". Our model, Video CoM, reasons through a Chain of Manipulations (CoM), performing iterative visual actions to gather and refine evidence. To support this behavior, we construct Video CoM Instruct, an 18K instruction tuning dataset curated for multi step manipulation reasoning. Beyond supervised learning, we further optimize the manipulation policy via reinforcement learning with reasoning aware Group Relative Policy Optimization (GRPO). Unlike prior work that relies solely on sparse answer rewards, our method introduces step level reasoning rewards, guiding the model toward grounded and consistent reasoning. Video CoM achieves strong results across nine video reasoning benchmarks, improving average performance by 3.6 percent over recent state of the art models, while training on only 25K SFT and 3K GRPO video samples, significantly fewer than comparable large scale models. Ablation studies demonstrate that reasoning aware rewards improve both accuracy and interpretability. Code: https://github.com/mbzuai-oryx/Video-CoM

Muhammad Maaz, Hanoona Rasheed, Salman Khan et al.

Building on the advances of language models, Large Multimodal Models (LMMs) have contributed significant improvements in video understanding. While the current video LMMs utilize advanced Large Language Models (LLMs), they rely on either image or video encoders to process visual inputs, each of which has its own limitations. Image encoders excel at capturing rich spatial details from frame sequences but lack explicit temporal context, which can be important in videos with intricate action sequences. On the other hand, video encoders provide temporal context but are often limited by computational constraints that lead to processing only sparse frames at lower resolutions, resulting in reduced contextual and spatial understanding. To this end, we introduce VideoGPT+, which combines the complementary benefits of the image encoder (for detailed spatial understanding) and the video encoder (for global temporal context modeling). The model processes videos by dividing them into smaller segments and applies an adaptive pooling strategy on features extracted by both image and video encoders. Our architecture showcases improved performance across multiple video benchmarks, including VCGBench, MVBench and Zero-shot question-answering. Further, we develop 112K video-instruction set using a novel semi-automatic annotation pipeline which further improves the model performance. Additionally, to comprehensively evaluate video LMMs, we present VCGBench-Diverse, covering 18 broad video categories such as lifestyle, sports, science, gaming, and surveillance videos. This benchmark with 4,354 question-answer pairs evaluates the generalization of existing LMMs on dense video captioning, spatial and temporal understanding, and complex reasoning, ensuring comprehensive assessment across diverse video types and dynamics. Code: https://github.com/mbzuai-oryx/VideoGPT-plus.

Hanoona Rasheed, Abdelrahman Shaker, Anqi Tang et al.

Mathematical reasoning in real-world video settings presents a fundamentally different challenge than in static images or text. It requires interpreting fine-grained visual information, accurately reading handwritten or digital text, and integrating spoken cues, often dispersed non-linearly over time. In such multimodal contexts, success hinges not just on perception, but on selectively identifying and integrating the right contextual details from a rich and noisy stream of content. To this end, we introduce VideoMathQA, a benchmark designed to evaluate whether models can perform such temporally extended cross-modal reasoning on videos. The benchmark spans 10 diverse mathematical domains, covering videos ranging from 10 seconds to over 1 hour. It requires models to interpret structured visual content, understand instructional narratives, and jointly ground concepts across visual, audio, and textual modalities. We employ graduate-level experts to ensure high quality, totaling over $920$ man-hours of annotation. To reflect real-world scenarios, questions are designed around three core reasoning challenges: direct problem solving, where answers are grounded in the presented question; conceptual transfer, which requires applying learned methods to new problems; and deep instructional comprehension, involving multi-step reasoning over extended explanations and partially worked-out solutions. Each question includes multi-step reasoning annotations, enabling fine-grained diagnosis of model capabilities. Through this benchmark, we highlight the limitations of existing approaches and establish a systematic evaluation framework for models that must reason, rather than merely perceive, across temporally extended and modality-rich mathematical problem settings. Our benchmark and evaluation code are available at: https://mbzuai-oryx.github.io/VideoMathQA

Muhammad Maaz, Hanoona Rasheed, Salman Khan et al.

What constitutes an object? This has been a long-standing question in computer vision. Towards this goal, numerous learning-free and learning-based approaches have been developed to score objectness. However, they generally do not scale well across new domains and novel objects. In this paper, we advocate that existing methods lack a top-down supervision signal governed by human-understandable semantics. For the first time in literature, we demonstrate that Multi-modal Vision Transformers (MViT) trained with aligned image-text pairs can effectively bridge this gap. Our extensive experiments across various domains and novel objects show the state-of-the-art performance of MViTs to localize generic objects in images. Based on the observation that existing MViTs do not include multi-scale feature processing and usually require longer training schedules, we develop an efficient MViT architecture using multi-scale deformable attention and late vision-language fusion. We show the significance of MViT proposals in a diverse range of applications including open-world object detection, salient and camouflage object detection, supervised and self-supervised detection tasks. Further, MViTs can adaptively generate proposals given a specific language query and thus offer enhanced interactability. Code: \url{https://git.io/J1HPY}.