Audio-Visual Camera Pose Estimation with Passive Scene Sounds and In-the-Wild Video

Understanding camera motion is a fundamental problem in embodied perception and 3D scene understanding. While visual methods have advanced rapidly, they often struggle under visually degraded conditions such as motion blur or occlusions. In this work, we show that passive scene sounds provide complementary cues for relative camera pose estimation for in-the-wild videos. We introduce a simple but effective audio-visual framework that integrates direction-ofarrival (DOA) spectra and binauralized embeddings into a state-of-the-art vision-only pose estimation model. Our results on two large datasets show consistent gains over strong visual baselines, plus robustness when the visual information is corrupted. To our knowledge, this represents the first work to successfully leverage audio for relative camera pose estimation in real-world videos, and it establishes incidental, everyday audio as an unexpected but promising signal for a classic spatial challenge. Project: http://vision.cs.utexas.edu/projects/av_camera_pose.

Learning Skill-Attributes for Transferable Assessment in Video

Skill assessment from video entails rating the quality of a person's physical performance and explaining what could be done better. Today's models specialize for an individual sport, and suffer from the high cost and scarcity of expert-level supervision across the long tail of sports. Towards closing that gap, we explore transferable video representations for skill assessment. Our CrossTrainer approach discovers skill-attributes, such as balance, control, and hand positioning -- whose meaning transcends the boundaries of any given sport, then trains a multimodal language model to generate actionable feedback for a novel video, e.g., "lift hands more to generate more power" as well as its proficiency level, e.g., early expert. We validate the new model on multiple datasets for both cross-sport (transfer) and intra-sport (in-domain) settings, where it achieves gains up to 60% relative to the state of the art. By abstracting out the shared behaviors indicative of human skill, the proposed video representation generalizes substantially better than an array of existing techniques, enriching today's multimodal large language models.

HieraMamba: Video Temporal Grounding via Hierarchical Anchor-Mamba Pooling

Video temporal grounding, the task of localizing the start and end times of a natural language query in untrimmed video, requires capturing both global context and fine-grained temporal detail. This challenge is particularly pronounced in long videos, where existing methods often compromise temporal fidelity by over-downsampling or relying on fixed windows. We present HieraMamba, a hierarchical architecture that preserves temporal structure and semantic richness across scales. At its core are Anchor-MambaPooling (AMP) blocks, which utilize Mamba's selective scanning to produce compact anchor tokens that summarize video content at multiple granularities. Two complementary objectives, anchor-conditioned and segment-pooled contrastive losses, encourage anchors to retain local detail while remaining globally discriminative. HieraMamba sets a new state-of-the-art on Ego4D-NLQ, MAD, and TACoS, demonstrating precise, temporally faithful localization in long, untrimmed videos.

PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding

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.

Learning Activity View-invariance Under Extreme Viewpoint Changes via Curriculum Knowledge Distillation

Traditional methods for view-invariant learning from video rely on controlled multi-view settings with minimal scene clutter. However, they struggle with in-the-wild videos that exhibit extreme viewpoint differences and share little visual content. We introduce a method for learning rich video representations in the presence of such severe view-occlusions. We first define a geometry-based metric that ranks views at a fine-grained temporal scale by their likely occlusion level. Then, using those rankings, we formulate a knowledge distillation objective that preserves action-centric semantics with a novel curriculum learning procedure that pairs incrementally more challenging views over time, thereby allowing smooth adaptation to extreme viewpoint differences. We evaluate our approach on two tasks, outperforming SOTA models on both temporal keystep grounding and fine-grained keystep recognition benchmarks - particularly on views that exhibit severe occlusion.

Stitch-a-Recipe: Video Demonstration from Multistep Descriptions

When obtaining visual illustrations from text descriptions, today's methods take a description with-a single text context caption, or an action description-and retrieve or generate the matching visual context. However, prior work does not permit visual illustration of multistep descriptions, e.g. a cooking recipe composed of multiple steps. Furthermore, simply handling each step description in isolation would result in an incoherent demonstration. We propose Stitch-a-Recipe, a novel retrieval-based method to assemble a video demonstration from a multistep description. The resulting video contains clips, possibly from different sources, that accurately reflect all the step descriptions, while being visually coherent. We formulate a training pipeline that creates large-scale weakly supervised data containing diverse and novel recipes and injects hard negatives that promote both correctness and coherence. Validated on in-the-wild instructional videos, Stitch-a-Recipe achieves state-of-the-art performance, with quantitative gains up to 24% as well as dramatic wins in a human preference study.

SPOC: Spatially-Progressing Object State Change Segmentation in Video

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

Switch-a-View: Few-Shot View Selection Learned from Edited Videos

We introduce Switch-a-View, a model that learns to automatically select the viewpoint to display at each timepoint when creating a how-to video. The key insight of our approach is how to train such a model from unlabeled--but human-edited--video samples. We pose a pretext task that pseudo-labels segments in the training videos for their primary viewpoint (egocentric or exocentric), and then discovers the patterns between those view-switch moments on the one hand and the visual and spoken content in the how-to video on the other hand. Armed with this predictor, our model then takes an unseen multi-view video as input and orchestrates which viewpoint should be displayed when. We further introduce a few-shot training setting that permits steering the model towards a new data domain. We demonstrate our idea on a variety of real-world video from HowTo100M and Ego-Exo4D and rigorously validate its advantages.

Progress-Aware Video Frame Captioning

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.

FIction: 4D Future Interaction Prediction from Video

Anticipating how a person will interact with objects in an environment is essential for activity understanding, but existing methods are limited to the 2D space of video frames-capturing physically ungrounded predictions of 'what' and ignoring the 'where' and 'how'. We introduce 4D future interaction prediction from videos. Given an input video of a human activity, the goal is to predict what objects at what 3D locations the person will interact with in the next time period (e.g., cabinet, fridge), and how they will execute that interaction (e.g., poses for bending, reaching, pulling). We propose a novel model FIction that fuses the past video observation of the person's actions and their environment to predict both the 'where' and 'how' of future interactions. Through comprehensive experiments on a variety of activities and real-world environments in Ego-Exo4D, we show that our proposed approach outperforms prior autoregressive and (lifted) 2D video models substantially, with more than 30% relative gains.