Zihui Xue

Kristen Grauman, Andrew Westbury, Lorenzo Torresani et al. · cmu, gatech

We present Ego-Exo4D, a diverse, large-scale multimodal multiview video dataset and benchmark challenge. Ego-Exo4D centers around simultaneously-captured egocentric and exocentric video of skilled human activities (e.g., sports, music, dance, bike repair). 740 participants from 13 cities worldwide performed these activities in 123 different natural scene contexts, yielding long-form captures from 1 to 42 minutes each and 1,286 hours of video combined. The multimodal nature of the dataset is unprecedented: the video is accompanied by multichannel audio, eye gaze, 3D point clouds, camera poses, IMU, and multiple paired language descriptions -- including a novel "expert commentary" done by coaches and teachers and tailored to the skilled-activity domain. To push the frontier of first-person video understanding of skilled human activity, we also present a suite of benchmark tasks and their annotations, including fine-grained activity understanding, proficiency estimation, cross-view translation, and 3D hand/body pose. All resources are open sourced to fuel new research in the community. Project page: http://ego-exo4d-data.org/

Zihui Xue, Kristen Grauman

The egocentric and exocentric viewpoints of a human activity look dramatically different, yet invariant representations to link them are essential for many potential applications in robotics and augmented reality. Prior work is limited to learning view-invariant features from paired synchronized viewpoints. We relax that strong data assumption and propose to learn fine-grained action features that are invariant to the viewpoints by aligning egocentric and exocentric videos in time, even when not captured simultaneously or in the same environment. To this end, we propose AE2, a self-supervised embedding approach with two key designs: (1) an object-centric encoder that explicitly focuses on regions corresponding to hands and active objects; and (2) a contrastive-based alignment objective that leverages temporally reversed frames as negative samples. For evaluation, we establish a benchmark for fine-grained video understanding in the ego-exo context, comprising four datasets -- including an ego tennis forehand dataset we collected, along with dense per-frame labels we annotated for each dataset. On the four datasets, our AE2 method strongly outperforms prior work in a variety of fine-grained downstream tasks, both in regular and cross-view settings.

Zihui Xue, Yale Song, Kristen Grauman et al.

Different video understanding tasks are typically treated in isolation, and even with distinct types of curated data (e.g., classifying sports in one dataset, tracking animals in another). However, in wearable cameras, the immersive egocentric perspective of a person engaging with the world around them presents an interconnected web of video understanding tasks -- hand-object manipulations, navigation in the space, or human-human interactions -- that unfold continuously, driven by the person's goals. We argue that this calls for a much more unified approach. We propose EgoTask Translation (EgoT2), which takes a collection of models optimized on separate tasks and learns to translate their outputs for improved performance on any or all of them at once. Unlike traditional transfer or multi-task learning, EgoT2's flipped design entails separate task-specific backbones and a task translator shared across all tasks, which captures synergies between even heterogeneous tasks and mitigates task competition. Demonstrating our model on a wide array of video tasks from Ego4D, we show its advantages over existing transfer paradigms and achieve top-ranked results on four of the Ego4D 2022 benchmark challenges.

Zihui Xue, Yale Song, Kristen Grauman et al.

This technical report describes the EgoTask Translation approach that explores relations among a set of egocentric video tasks in the Ego4D challenge. To improve the primary task of interest, we propose to leverage existing models developed for other related tasks and design a task translator that learns to ''translate'' auxiliary task features to the primary task. With no modification to the baseline architectures, our proposed approach achieves competitive performance on two Ego4D challenges, ranking the 1st in the talking to me challenge and the 3rd in the PNR keyframe localization challenge.

Zihui Xue, Zhengqi Gao, Sucheng Ren et al.

Crossmodal knowledge distillation (KD) extends traditional knowledge distillation to the area of multimodal learning and demonstrates great success in various applications. To achieve knowledge transfer across modalities, a pretrained network from one modality is adopted as the teacher to provide supervision signals to a student network learning from another modality. In contrast to the empirical success reported in prior works, the working mechanism of crossmodal KD remains a mystery. In this paper, we present a thorough understanding of crossmodal KD. We begin with two case studies and demonstrate that KD is not a universal cure in crossmodal knowledge transfer. We then present the modality Venn diagram to understand modality relationships and the modality focusing hypothesis revealing the decisive factor in the efficacy of crossmodal KD. Experimental results on 6 multimodal datasets help justify our hypothesis, diagnose failure cases, and point directions to improve crossmodal knowledge transfer in the future.

Zihui Xue, Kristen Grauman, Dima Damen et al.

Can one perceive a video's content without seeing its pixels, just from the camera trajectory-the path it carves through space? This paper is the first to systematically investigate this seemingly implausible question. Towards this end, we propose a contrastive learning framework to train CamFormer, a dedicated encoder that projects camera pose trajectories into a joint embedding space, aligning them with natural language. We find that, contrary to its apparent simplicity, the camera trajectory is a remarkably informative signal to uncover video content. In other words, "how you move" can indeed reveal "what you are doing" (egocentric) or "observing" (exocentric). We demonstrate the versatility of our learned CamFormer embeddings on a diverse suite of downstream tasks, ranging from cross-modal alignment to classification and temporal analysis. Importantly, our representations are robust across diverse camera pose estimation methods, including both high-fidelity multi-sensored and standard RGB-only estimators. Our findings establish camera trajectory as a lightweight, robust, and versatile modality for perceiving video content.

Zhengqi Gao, Sucheng Ren, Zihui Xue et al.

Multimodal fusion emerges as an appealing technique to improve model performances on many tasks. Nevertheless, the robustness of such fusion methods is rarely involved in the present literature. In this paper, we propose a training-free robust late-fusion method by exploiting conditional independence assumption and Jacobian regularization. Our key is to minimize the Frobenius norm of a Jacobian matrix, where the resulting optimization problem is relaxed to a tractable Sylvester equation. Furthermore, we provide a theoretical error bound of our method and some insights about the function of the extra modality. Several numerical experiments on AV-MNIST, RAVDESS, and VGGsound demonstrate the efficacy of our method under both adversarial attacks and random corruptions.

Ami Baid, Zihui Xue, Kristen Grauman

While Audio-Visual Language Models (AVLMs) have achieved remarkable progress over recent years, their reliability is bottlenecked by cross-modal hallucination. A particularly pervasive manifestation is video-driven audio hallucination: models routinely exploit visual shortcuts to hallucinate expected sounds, discarding true auditory evidence. To counteract this deeply ingrained visual dominance, we propose Audio-Contrastive Preference Optimization (ACPO). This dual-axis preference learning framework introduces an output-contrastive objective to penalize visual descriptions masquerading as audio facts, alongside an input-contrastive objective that swaps audio tracks to explicitly penalize generation invariant to the true auditory signal. Extensive experiments demonstrate that ACPO establishes highly faithful audio grounding and mitigates audio hallucination without compromising overarching multimodal capabilities.

Zihui Xue, Ami Baid, Sangho Kim et al.

As wearable devices like smart glasses integrate Large Multimodal Models (LMMs) into the continuous first-person visual streams of individual users, the evolution of these models into true personal assistants hinges on visual personalization: the ability to reason over visual information unique to the wearer. We formalize this capability as Personal Visual Context Learning (Personal VCL), the prompt-time capability of using user-specific visual context to resolve personalized queries. To systematically evaluate this, we present Personal-VCL-Bench, a comprehensive benchmark capturing the personal visual world across persons, objects, and behaviors. Our analysis of frontier LMMs identifies a profound context utilization gap, revealing that the mechanisms for leveraging visual evidence, as well as aggregating multiple visual observations, remain critically understudied. Motivated by these findings, we propose the Agentic Context Bank, a strong inference-time baseline that structures a user's visual context into a self-refining memory bank and employs query-adaptive evidence selection. Our baseline approach consistently improves over standard context prompting regimes across tasks and evaluated backbones, demonstrating a practical path towards future personalized LMMs.

Zihui Xue, Kumar Ashutosh, Kristen Grauman

Object State Changes (OSCs) are pivotal for video understanding. While humans can effortlessly generalize OSC understanding from familiar to unknown objects, current approaches are confined to a closed vocabulary. Addressing this gap, we introduce a novel open-world formulation for the video OSC problem. The goal is to temporally localize the three stages of an OSC -- the object's initial state, its transitioning state, and its end state -- whether or not the object has been observed during training. Towards this end, we develop VidOSC, a holistic learning approach that: (1) leverages text and vision-language models for supervisory signals to obviate manually labeling OSC training data, and (2) abstracts fine-grained shared state representations from objects to enhance generalization. Furthermore, we present HowToChange, the first open-world benchmark for video OSC localization, which offers an order of magnitude increase in the label space and annotation volume compared to the best existing benchmark. Experimental results demonstrate the efficacy of our approach, in both traditional closed-world and open-world scenarios.

Mi Luo, Zihui Xue, Alex Dimakis et al.

We investigate exocentric-to-egocentric cross-view translation, which aims to generate a first-person (egocentric) view of an actor based on a video recording that captures the actor from a third-person (exocentric) perspective. To this end, we propose a generative framework called Exo2Ego that decouples the translation process into two stages: high-level structure transformation, which explicitly encourages cross-view correspondence between exocentric and egocentric views, and a diffusion-based pixel-level hallucination, which incorporates a hand layout prior to enhance the fidelity of the generated egocentric view. To pave the way for future advancements in this field, we curate a comprehensive exo-to-ego cross-view translation benchmark. It consists of a diverse collection of synchronized ego-exo tabletop activity video pairs sourced from three public datasets: H2O, Aria Pilot, and Assembly101. The experimental results validate that Exo2Ego delivers photorealistic video results with clear hand manipulation details and outperforms several baselines in terms of both synthesis quality and generalization ability to new actions.

Kumar Ashutosh, Zihui Xue, Tushar Nagarajan et al.

We introduce the video detours problem for navigating instructional videos. Given a source video and a natural language query asking to alter the how-to video's current path of execution in a certain way, the goal is to find a related ''detour video'' that satisfies the requested alteration. To address this challenge, we propose VidDetours, a novel video-language approach that learns to retrieve the targeted temporal segments from a large repository of how-to's using video-and-text conditioned queries. Furthermore, we devise a language-based pipeline that exploits how-to video narration text to create weakly supervised training data. We demonstrate our idea applied to the domain of how-to cooking videos, where a user can detour from their current recipe to find steps with alternate ingredients, tools, and techniques. Validating on a ground truth annotated dataset of 16K samples, we show our model's significant improvements over best available methods for video retrieval and question answering, with recall rates exceeding the state of the art by 35%.

Zhengqi Gao, Kaiwen Zha, Tianyuan Zhang et al.

Guidance techniques are simple yet effective for improving conditional generation in diffusion models. Albeit their empirical success, the practical implementation of guidance diverges significantly from its theoretical motivation. In this paper, we reconcile this discrepancy by replacing the scaled marginal distribution target, which we prove theoretically invalid, with a valid scaled joint distribution objective. Additionally, we show that the established guidance implementations are approximations to the intractable optimal solution under no future foresight constraint. Building on these theoretical insights, we propose rectified gradient guidance (REG), a versatile enhancement designed to boost the performance of existing guidance methods. Experiments on 1D and 2D demonstrate that REG provides a better approximation to the optimal solution than prior guidance techniques, validating the proposed theoretical framework. Extensive experiments on class-conditional ImageNet and text-to-image generation tasks show that incorporating REG consistently improves FID and Inception/CLIP scores across various settings compared to its absence.

Zihui Xue, Joungbin An, Xitong Yang et al.

While image captioning provides isolated descriptions for individual images, and video captioning offers one single narrative for an entire video clip, our work explores an important middle ground: progress-aware video captioning at the frame level. This novel task aims to generate temporally fine-grained captions that not only accurately describe each frame but also capture the subtle progression of actions throughout a video sequence. Despite the strong capabilities of existing leading vision language models, they often struggle to discern the nuances of frame-wise differences. To address this, we propose ProgressCaptioner, a captioning model designed to capture the fine-grained temporal dynamics within an action sequence. Alongside, we develop the FrameCap dataset to support training and the FrameCapEval benchmark to assess caption quality. The results demonstrate that ProgressCaptioner significantly surpasses leading captioning models, producing precise captions that accurately capture action progression and set a new standard for temporal precision in video captioning. Finally, we showcase practical applications of our approach, specifically in aiding keyframe selection and advancing video understanding, highlighting its broad utility.

Mina Huh, Zihui Xue, Ujjaini Das et al.

People use videos to learn new recipes, exercises, and crafts. Such videos remain difficult for blind and low vision (BLV) people to follow as they rely on visual comparison. Our observations of visual rehabilitation therapists (VRTs) guiding BLV people to follow how-to videos revealed that VRTs provide both proactive and responsive support including detailed descriptions, non-visual workarounds, and progress feedback. We propose Vid2Coach, a system that transforms how-to videos into wearable camera-based assistants that provide accessible instructions and mixed-initiative feedback. From the video, Vid2Coach generates accessible instructions by augmenting narrated instructions with demonstration details and completion criteria for each step. It then uses retrieval-augmented-generation to extract relevant non-visual workarounds from BLV-specific resources. Vid2Coach then monitors user progress with a camera embedded in commercial smart glasses to provide context-aware instructions, proactive feedback, and answers to user questions. BLV participants (N=8) using Vid2Coach completed cooking tasks with 58.5\% fewer errors than when using their typical workflow and wanted to use Vid2Coach in their daily lives. Vid2Coach demonstrates an opportunity for AI visual assistance that strengthens rather than replaces non-visual expertise.

Zihui Xue, Mi Luo, Kristen Grauman

The Arrow of Time (AoT)-time's irreversible flow shaping physical events-is fundamental to video comprehension, yet remains a significant challenge for modern large multimodal models (LMMs). Current LMMs struggle to perceive and utilize temporal directionality in video when responding to language queries, obstructing deeper temporal understanding. We tackle this deficiency by first providing a critical analysis of existing benchmarks and models. We then introduce ArrowRL, a reinforcement learning (RL)-based training strategy with an innovative reverse reward that instills AoT awareness by encouraging divergent video interpretations between forward and reversed visual frames. For rigorous evaluation, we additionally develop AoTBench, a new multi-faceted benchmark probing temporally challenging questions. Experiments show ArrowRL greatly advances temporal perception: it not only achieves substantial improvements on our challenging AoTBench but also demonstrably boosts performance on standard video question answering (VQA) benchmarks (with peak accuracy gains reaching over 20% and 10% respectively). This validates ArrowRL's effectiveness and highlights the critical need for dedicated AoT understanding in LMMs.

Mi Luo, Zihui Xue, Alex Dimakis et al.

Video reasoning, the task of enabling machines to infer from dynamic visual content through multi-step logic, is crucial for advanced AI. While the Chain-of-Thought (CoT) mechanism has enhanced reasoning in text-based tasks, its application to video understanding remains underexplored. This paper presents a systematic analysis revealing that CoT often degrades performance in video reasoning, generating verbose but misleading internal monologues, and leading to hallucinated visual details and overridden correct intuitions - a phenomenon we term "visual thinking drift". We explain this drift through a Bayesian lens, positing that CoT traces often diverge from actual visual evidence, instead amplifying internal biases or language priors, causing models to storytell rather than engage in grounded reasoning. To counteract this, we introduce Visual Evidence Reward (VER), a novel reinforcement learning framework that explicitly rewards the generation of reasoning traces that are verifiably grounded in visual evidence. Comprehensive evaluation across 10 diverse video understanding benchmarks demonstrates that our Video-VER consistently achieves top performance. Our work sheds light on the distinct challenges of video-centric reasoning and encourages the development of AI that robustly grounds its inferences in visual evidence - for large multimodal models that not only "think before answering", but also "see while thinking".

Priyanka Mandikal, Tushar Nagarajan, Alex Stoken et al.

Object state changes in video reveal critical information about human and agent activity. However, existing methods are limited to temporal localization of when the object is in its initial state (e.g., the unchopped avocado) versus when it has completed a state change (e.g., the chopped avocado), which limits applicability for any task requiring detailed information about the progress of the actions and its spatial localization. We propose to deepen the problem by introducing the spatially-progressing object state change segmentation task. The goal is to segment at the pixel-level those regions of an object that are actionable and those that are transformed. We introduce the first model to address this task, designing a VLM-based pseudo-labeling approach, state-change dynamics constraints, and a novel WhereToChange benchmark built on in-the-wild Internet videos. Experiments on two datasets validate both the challenge of the new task as well as the promise of our model for localizing exactly where and how fast objects are changing in video. We further demonstrate useful implications for tracking activity progress to benefit robotic agents. Project page: https://vision.cs.utexas.edu/projects/spoc-spatially-progressing-osc

Changan Chen, Puyuan Peng, Ami Baid et al.

Generating realistic audio for human actions is important for many applications, such as creating sound effects for films or virtual reality games. Existing approaches implicitly assume total correspondence between the video and audio during training, yet many sounds happen off-screen and have weak to no correspondence with the visuals -- resulting in uncontrolled ambient sounds or hallucinations at test time. We propose a novel ambient-aware audio generation model, AV-LDM. We devise a novel audio-conditioning mechanism to learn to disentangle foreground action sounds from the ambient background sounds in in-the-wild training videos. Given a novel silent video, our model uses retrieval-augmented generation to create audio that matches the visual content both semantically and temporally. We train and evaluate our model on two in-the-wild egocentric video datasets, Ego4D and EPIC-KITCHENS, and we introduce Ego4D-Sounds -- 1.2M curated clips with action-audio correspondence. Our model outperforms an array of existing methods, allows controllable generation of the ambient sound, and even shows promise for generalizing to computer graphics game clips. Overall, our approach is the first to focus video-to-audio generation faithfully on the observed visual content despite training from uncurated clips with natural background sounds.

Zihui Xue, Mi Luo, Changan Chen et al.

We study the problem of precisely swapping objects in videos, with a focus on those interacted with by hands, given one user-provided reference object image. Despite the great advancements that diffusion models have made in video editing recently, these models often fall short in handling the intricacies of hand-object interactions (HOI), failing to produce realistic edits -- especially when object swapping results in object shape or functionality changes. To bridge this gap, we present HOI-Swap, a novel diffusion-based video editing framework trained in a self-supervised manner. Designed in two stages, the first stage focuses on object swapping in a single frame with HOI awareness; the model learns to adjust the interaction patterns, such as the hand grasp, based on changes in the object's properties. The second stage extends the single-frame edit across the entire sequence; we achieve controllable motion alignment with the original video by: (1) warping a new sequence from the stage-I edited frame based on sampled motion points and (2) conditioning video generation on the warped sequence. Comprehensive qualitative and quantitative evaluations demonstrate that HOI-Swap significantly outperforms existing methods, delivering high-quality video edits with realistic HOIs.

Zihui Xue, Radu Marculescu

Deep multimodal learning has achieved great progress in recent years. However, current fusion approaches are static in nature, i.e., they process and fuse multimodal inputs with identical computation, without accounting for diverse computational demands of different multimodal data. In this work, we propose dynamic multimodal fusion (DynMM), a new approach that adaptively fuses multimodal data and generates data-dependent forward paths during inference. To this end, we propose a gating function to provide modality-level or fusion-level decisions on-the-fly based on multimodal features and a resource-aware loss function that encourages computational efficiency. Results on various multimodal tasks demonstrate the efficiency and wide applicability of our approach. For instance, DynMM can reduce the computation costs by 46.5% with only a negligible accuracy loss (CMU-MOSEI sentiment analysis) and improve segmentation performance with over 21% savings in computation (NYU Depth V2 semantic segmentation) when compared with static fusion approaches. We believe our approach opens a new direction towards dynamic multimodal network design, with applications to a wide range of multimodal tasks.

Zihui Xue, Yuedong Yang, Mengtian Yang et al.

Graph Neural Networks (GNNs) have demonstrated a great potential in a variety of graph-based applications, such as recommender systems, drug discovery, and object recognition. Nevertheless, resource-efficient GNN learning is a rarely explored topic despite its many benefits for edge computing and Internet of Things (IoT) applications. To improve this state of affairs, this work proposes efficient subgraph-level training via resource-aware graph partitioning (SUGAR). SUGAR first partitions the initial graph into a set of disjoint subgraphs and then performs local training at the subgraph-level. We provide a theoretical analysis and conduct extensive experiments on five graph benchmarks to verify its efficacy in practice. Our results show that SUGAR can achieve up to 33 times runtime speedup and 3.8 times memory reduction on large-scale graphs. We believe SUGAR opens a new research direction towards developing GNN methods that are resource-efficient, hence suitable for IoT deployment.

Sucheng Ren, Zhengqi Gao, Tianyu Hua et al.

Transformers recently are adapted from the community of natural language processing as a promising substitute of convolution-based neural networks for visual learning tasks. However, its supremacy degenerates given an insufficient amount of training data (e.g., ImageNet). To make it into practical utility, we propose a novel distillation-based method to train vision transformers. Unlike previous works, where merely heavy convolution-based teachers are provided, we introduce lightweight teachers with different architectural inductive biases (e.g., convolution and involution) to co-advise the student transformer. The key is that teachers with different inductive biases attain different knowledge despite that they are trained on the same dataset, and such different knowledge compounds and boosts the student's performance during distillation. Equipped with this cross inductive bias distillation method, our vision transformers (termed as CivT) outperform all previous transformers of the same architecture on ImageNet.

Yu Huang, Chenzhuang Du, Zihui Xue et al.

The world provides us with data of multiple modalities. Intuitively, models fusing data from different modalities outperform their uni-modal counterparts, since more information is aggregated. Recently, joining the success of deep learning, there is an influential line of work on deep multi-modal learning, which has remarkable empirical results on various applications. However, theoretical justifications in this field are notably lacking. Can multi-modal learning provably perform better than uni-modal? In this paper, we answer this question under a most popular multi-modal fusion framework, which firstly encodes features from different modalities into a common latent space and seamlessly maps the latent representations into the task space. We prove that learning with multiple modalities achieves a smaller population risk than only using its subset of modalities. The main intuition is that the former has a more accurate estimate of the latent space representation. To the best of our knowledge, this is the first theoretical treatment to capture important qualitative phenomena observed in real multi-modal applications from the generalization perspective. Combining with experiment results, we show that multi-modal learning does possess an appealing formal guarantee.

Tianyu Hua, Wenxiao Wang, Zihui Xue et al.

In self-supervised representation learning, a common idea behind most of the state-of-the-art approaches is to enforce the robustness of the representations to predefined augmentations. A potential issue of this idea is the existence of completely collapsed solutions (i.e., constant features), which are typically avoided implicitly by carefully chosen implementation details. In this work, we study a relatively concise framework containing the most common components from recent approaches. We verify the existence of complete collapse and discover another reachable collapse pattern that is usually overlooked, namely dimensional collapse. We connect dimensional collapse with strong correlations between axes and consider such connection as a strong motivation for feature decorrelation (i.e., standardizing the covariance matrix). The gains from feature decorrelation are verified empirically to highlight the importance and the potential of this insight.

Zihui Xue, Sucheng Ren, Zhengqi Gao et al.

The popularity of multimodal sensors and the accessibility of the Internet have brought us a massive amount of unlabeled multimodal data. Since existing datasets and well-trained models are primarily unimodal, the modality gap between a unimodal network and unlabeled multimodal data poses an interesting problem: how to transfer a pre-trained unimodal network to perform the same task on unlabeled multimodal data? In this work, we propose multimodal knowledge expansion (MKE), a knowledge distillation-based framework to effectively utilize multimodal data without requiring labels. Opposite to traditional knowledge distillation, where the student is designed to be lightweight and inferior to the teacher, we observe that a multimodal student model consistently denoises pseudo labels and generalizes better than its teacher. Extensive experiments on four tasks and different modalities verify this finding. Furthermore, we connect the mechanism of MKE to semi-supervised learning and offer both empirical and theoretical explanations to understand the denoising capability of a multimodal student.