Jason J. Corso

Filippos Bellos, NaveenJohn Premkumar, Yannis Avrithis et al.

LLM-for-time series (TS) methods typically treat time shallowly, injecting positional or prompt-based cues once at the input of a largely frozen decoder, which limits temporal reasoning as this information degrades through the layers. We introduce Temporal-Prior Conditioning (TPC), which elevates time to a first-class modality that conditions the model at multiple depths. TPC attaches a small set of learnable time series tokens to the patch stream; at selected layers these tokens cross-attend to temporal embeddings derived from compact, human-readable temporal descriptors encoded by the same frozen LLM, then feed temporal context back via self-attention. This disentangles time series signal and temporal information while maintaining a low parameter budget. We show that by training only the cross-attention modules and explicitly disentangling time series signal and temporal information, TPC consistently outperforms both full fine-tuning and shallow conditioning strategies, achieving state-of-the-art performance in long-term forecasting across diverse datasets. Code available at: https://github.com/fil-mp/Deep_tpc

Nathan Louis, Tylan N. Templin, Travis D. Eliason et al.

Analyzing sports performance or preventing injuries requires capturing ground reaction forces (GRFs) exerted by the human body during certain movements. Standard practice uses physical markers paired with force plates in a controlled environment, but this is marred by high costs, lengthy implementation time, and variance in repeat experiments; hence, we propose GRF inference from video. While recent work has used LSTMs to estimate GRFs from 2D viewpoints, these can be limited in their modeling and representation capacity. First, we propose using a transformer architecture to tackle the GRF from video task, being the first to do so. Then we introduce a new loss to minimize high impact peaks in regressed curves. We also show that pre-training and multi-task learning on 2D-to-3D human pose estimation improves generalization to unseen motions. And pre-training on this different task provides good initial weights when finetuning on smaller (rarer) GRF datasets. We evaluate on LAAS Parkour and a newly collected ForcePose dataset; we show up to 19% decrease in error compared to prior approaches.

Madan Ravi Ganesh, Salimeh Yasaei Sekeh, Jason J. Corso

Raw deep neural network (DNN) performance is not enough; in real-world settings, computational load, training efficiency and adversarial security are just as or even more important. We propose to simultaneously tackle Performance, Efficiency, and Robustness, using our proposed algorithm Q-TART, Quickly Train for Adversarial Robustness and in-Transferability. Q-TART follows the intuition that samples highly susceptible to noise strongly affect the decision boundaries learned by DNNs, which in turn degrades their performance and adversarial susceptibility. By identifying and removing such samples, we demonstrate improved performance and adversarial robustness while using only a subset of the training data. Through our experiments we highlight Q-TART's high performance across multiple Dataset-DNN combinations, including ImageNet, and provide insights into the complementary behavior of Q-TART alongside existing adversarial training approaches to increase robustness by over 1.3% while using up to 17.9% less training time.

Filippos Bellos, Yutong Li, Jessie N Dong et al.

Point-of-care transthoracic echocardiography (TTE) enables cardiac assessment in virtually any clinical setting, yet its diagnostic utility remains constrained by the expertise required for image acquisition and interpretation. Visual question answering (VQA) offers a promising paradigm for bridging this expertise gap through interactive clinical assistance, but existing echocardiography VQA datasets are limited in scale, restricted to high-quality images, and only cover a few views. We introduce EchoVQA, the first large-scale VQA dataset for echocardiography, comprising 14,299 images and 74,819 question-answer pairs. The dataset integrates public sources (EchoNet-Dynamic, CAMUS) with our own point-of-care acquisitions from two handheld probes (Lumify, Clarius), spanning diverse views and including both high-quality and suboptimal images. Uniquely, EchoVQA includes acquisition guidance questions to help users optimize transducer positioning toward a diagnostic apical 4-chamber view for left ventricular ejection fraction estimation -- a challenging task for novice operators in point-of-care settings. We further develop a parameter-efficient method based on multimodal learnable prompts achieving state-of-the-art performance on most benchmarks, including EchoVQA, with significantly less trainable parameters than existing state-of-the-art approaches.

Brent A. Griffin, Jacob Marks, Jason J. Corso

Deep learning increasingly relies on massive data with substantial costs for storage, annotation, and model training. To reduce these costs, coreset selection aims to find a representative subset of data to train models while ideally performing on par with the full data training. State-of-the-art coreset methods use carefully-designed criteria to quantify the importance of each data example via ground truth labels and dataset-specific training, then select examples whose scores lie in a certain range to construct a coreset. These methods work well in their respective settings, however, they cannot select data that are unlabeled, which is the majority of real-world data. To that end, this paper motivates and formalizes the problem of unlabeled coreset selection to enable greater scale and reduce annotation costs for deep learning. As a solution, we develop Zero-Shot Coreset Selection (ZCore), a method that efficiently selects coresets without ground truth labels or training on candidate data. Instead, ZCore uses existing foundation models to generate a zero-shot embedding space for unlabeled data, then quantifies the relative importance of each example based on overall coverage and redundancy within the embedding distribution. We evaluate ZCore on four datasets and outperform several state-of-the-art label-based methods, leading to a strong baseline for future research in unlabeled coreset selection. On ImageNet, ZCore selections achieve a downstream model accuracy of 53.99% with only 10% training data, which outperforms label-based methods while removing annotation requirements for 1.15 million images. Our code is publicly available at https://github.com/voxel51/zcore.

Yayuan Li, Chenglin Li, Jingying Wang et al.

Instructional videos are the dominant medium for learning physical tasks, yet they rarely match the user's real-world visual context. Motor simulation and cognitive load theories predict this mismatch should matter, but we do not know (1) how much it could affect task completion, (2) which visual attributes are responsible, and (3) how users experience it. We conduct two complementary studies (56 participants, 86+ hours, four first-aid and culinary tasks) in which we use Wizard-of-Oz recordings to control the degree of visual alignment in instructional videos. In Study 1 (N=16), we prepare In-Context instructional videos (ICON) -- fully aligned with the user's visual perception -- to compare against business-as-usual Internet videos. ICON yields statistically significant improvements: 11.1% higher completion quality and 15.5% faster completion. Qualitative analysis reveals four visual context attributes responsible for the effect: Task Object Intrinsics, Task Object State, Environmental Context, and Observational Context. Study 2 (N=40) ablates each attribute by systematically misaligning one at a time from an otherwise fully aligned video, confirming all four produce consistent degradation. However, we find users fail to perceive the effect of single-attribute misalignment on task performance despite clear drops in objective measurement. Visual context misalignment is substantial, decomposable, and invisible to the user. These findings help understand the effect of visual context mismatch and how we should evaluate instructional videos for physical task guidance.

Zaiyang Guo, Jessie N. Dong, Filippos Bellos et al.

Point-of-care transthoracic echocardiography (TTE) makes it possible to assess a patient's cardiac function in almost any setting. A critical step in the TTE exam is acquisition of the apical 4-chamber (A4CH) view, which is used to evaluate clinically impactful measurements such as left ventricular ejection fraction (LVEF). However, optimizing transducer pose for high-quality image acquisition and subsequent measurement is a challenging task, particularly for novice users. In this work, we present a multi-task network that provides feedback cues for A4CH view acquisition and automatically estimates LVEF in high-quality A4CH images. The network cascades a transducer pose scoring module and an uncertainty-aware LV landmark detector with automated LVEF estimation. A strength is that network training and inference do not require cumbersome or costly setups for transducer position tracking. We evaluate performance on point-of-care TTE data acquired with a spatially dense "sweep" protocol around the optimal A4CH view. The results demonstrate the network's ability to determine when the transducer pose is on target, close to target, or far from target based on the images alone, while generating visual landmark cues that guide anatomical interpretation and orientation. In conclusion, we demonstrate a promising strategy to provide guidance for A4CH view acquisition, which may be useful when deploying point-of-care TTE in limited resource settings.

Jacob Marks, Brent A. Griffin, Jason J. Corso

We introduce a new framework for analyzing classification datasets based on the ratios of reconstruction errors between autoencoders trained on individual classes. This analysis framework enables efficient characterization of datasets on the sample, class, and entire dataset levels. We define reconstruction error ratios (RERs) that probe classification difficulty and allow its decomposition into (1) finite sample size and (2) Bayes error and decision-boundary complexity. Through systematic study across 19 popular visual datasets, we find that our RER-based dataset difficulty probe strongly correlates with error rate for state-of-the-art (SOTA) classification models. By interpreting sample-level classification difficulty as a label mistakenness score, we further find that RERs achieve SOTA performance on mislabel detection tasks on hard datasets under symmetric and asymmetric label noise. Our code is publicly available at https://github.com/voxel51/reconstruction-error-ratios.

Ryan Szeto, Jason J. Corso

Quantitative evaluation has increased dramatically among recent video inpainting work, but the video and mask content used to gauge performance has received relatively little attention. Although attributes such as camera and background scene motion inherently change the difficulty of the task and affect methods differently, existing evaluation schemes fail to control for them, thereby providing minimal insight into inpainting failure modes. To address this gap, we propose the Diagnostic Evaluation of Video Inpainting on Landscapes (DEVIL) benchmark, which consists of two contributions: (i) a novel dataset of videos and masks labeled according to several key inpainting failure modes, and (ii) an evaluation scheme that samples slices of the dataset characterized by a fixed content attribute, and scores performance on each slice according to reconstruction, realism, and temporal consistency quality. By revealing systematic changes in performance induced by particular characteristics of the input content, our challenging benchmark enables more insightful analysis into video inpainting methods and serves as an invaluable diagnostic tool for the field. Our code and data are available at https://github.com/MichiganCOG/devil .

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.

Hao Tang, Dan Xu, Nicu Sebe et al.

Cross-view image translation is challenging because it involves images with drastically different views and severe deformation. In this paper, we propose a novel approach named Multi-Channel Attention SelectionGAN (SelectionGAN) that makes it possible to generate images of natural scenes in arbitrary viewpoints, based on an image of the scene and a novel semantic map. The proposed SelectionGAN explicitly utilizes the semantic information and consists of two stages. In the first stage, the condition image and the target semantic map are fed into a cycled semantic-guided generation network to produce initial coarse results. In the second stage, we refine the initial results by using a multi-channel attention selection mechanism. Moreover, uncertainty maps automatically learned from attentions are used to guide the pixel loss for better network optimization. Extensive experiments on Dayton, CVUSA and Ego2Top datasets show that our model is able to generate significantly better results than the state-of-the-art methods. The source code, data and trained models are available at https://github.com/Ha0Tang/SelectionGAN.

Abhishek Venkataraman, Brent Griffin, Jason J. Corso

Next generation robots will need to understand intricate and articulated objects as they cooperate in human environments. To do so, these robots will need to move beyond their current abilities--- working with relatively simple objects in a task-indifferent manner--- toward more sophisticated abilities that dynamically estimate the properties of complex, articulated objects. To that end, we make two compelling contributions toward general articulated (physical) object understanding in this paper. First, we introduce a new dataset, SPARE: Simulated and Physical ARticulated Extendable dataset. SPARE is an extendable open-source dataset providing equivalent simulated and physical instances of articulated objects (kinematic chains), providing the greater research community with a training and evaluation tool for methods generating kinematic descriptions of articulated objects. To the best of our knowledge, this is the first joint visual and physical (3D-printable) dataset for the Vision community. Second, we present a deep neural network that can predit the number of links and the length of the links of an articulated object. These new ideas outperform classical approaches to understanding kinematic chains, such tracking-based methods, which fail in the case of occlusion and do not leverage multiple views when available.

Ryan Szeto, Simon Stent, German Ros et al.

We present a parameterized synthetic dataset called Moving Symbols to support the objective study of video prediction networks. Using several instantiations of the dataset in which variation is explicitly controlled, we highlight issues in an existing state-of-the-art approach and propose the use of a performance metric with greater semantic meaning to improve experimental interpretability. Our dataset provides canonical test cases that will help the community better understand, and eventually improve, the representations learned by such networks in the future. Code is available at https://github.com/rszeto/moving-symbols .

Chenliang Xu, Richard F. Doell, Stephen José Hanson et al.

Existing methods in the semantic computer vision community seem unable to deal with the explosion and richness of modern, open-source and social video content. Although sophisticated methods such as object detection or bag-of-words models have been well studied, they typically operate on low level features and ultimately suffer from either scalability issues or a lack of semantic meaning. On the other hand, video supervoxel segmentation has recently been established and applied to large scale data processing, which potentially serves as an intermediate representation to high level video semantic extraction. The supervoxels are rich decompositions of the video content: they capture object shape and motion well. However, it is not yet known if the supervoxel segmentation retains the semantics of the underlying video content. In this paper, we conduct a systematic study of how well the actor and action semantics are retained in video supervoxel segmentation. Our study has human observers watching supervoxel segmentation videos and trying to discriminate both actor (human or animal) and action (one of eight everyday actions). We gather and analyze a large set of 640 human perceptions over 96 videos in 3 different supervoxel scales. Furthermore, we conduct machine recognition experiments on a feature defined on supervoxel segmentation, called supervoxel shape context, which is inspired by the higher order processes in human perception. Our ultimate findings suggest that a significant amount of semantics have been well retained in the video supervoxel segmentation and can be used for further video analysis.

Tin Stribor Sohn, Maximilian Dillitzer, Jason J. Corso et al.

Humans perceive and reason about their surroundings in four dimensions by building persistent, structured internal representations that encode semantic meaning, spatial layout, and temporal dynamics. These multimodal memories enable them to recall past events, infer unobserved states, and integrate new information into context-dependent reasoning. Inspired by this capability, we introduce R4, a training-free framework for retrieval-augmented reasoning in 4D spatio-temporal space that equips vision-language models (VLMs) with structured, lifelong memory. R4 continuously constructs a 4D knowledge database by anchoring object-level semantic descriptions in metric space and time, yielding a persistent world model that can be shared across agents. At inference, natural language queries are decomposed into semantic, spatial, and temporal keys to retrieve relevant observations, which are integrated into the VLM's reasoning. Unlike classical retrieval-augmented generation methods, retrieval in R4 operates directly in 4D space, enabling episodic and collaborative reasoning without training. Experiments on embodied question answering and navigation benchmarks demonstrate that R4 substantially improves retrieval and reasoning over spatio-temporal information compared to baselines, advancing a new paradigm for embodied 4D reasoning in dynamic environments.

Tin Stribor Sohn, Maximilian Dillitzer, Jason J. Corso et al.

Vision-language navigation requires agents to reason and act under constraints of embodiment. While vision-language models (VLMs) demonstrate strong generalization, current benchmarks provide limited understanding of how embodiment -- i.e., the choice of physical platform, sensor configuration, and modality alignment -- influences perception, reasoning, and control. We introduce Embodied4C, a closed-loop benchmark designed as a Turing test for embodied reasoning. The benchmark evaluates the core embodied capabilities of VLMs across three heterogeneous embodiments -- autonomous vehicles, aerial drones, and robotic manipulators -- through approximately 1.1K one-shot reasoning questions and 58 goal-directed navigation tasks. These tasks jointly assess four foundational dimensions: semantic, spatial, temporal, and physical reasoning. Each embodiment presents dynamic sensor configurations and environment variations to probe generalization beyond platform-specific adaptation. To prevent embodiment overfitting, Embodied4C integrates domain-far queries targeting abstract and cross-context reasoning. Comprehensive evaluation across ten state-of-the-art VLMs and four embodied control baselines shows that cross-modal alignment and instruction tuning matter more than scale, while spatial and temporal reasoning remains the primary bottleneck for reliable embodied competence.

Tin Stribor Sohn, Maximilian Dillitzer, Jason J. Corso et al.

Autonomous robotic systems require spatio-temporal understanding of dynamic environments to ensure reliable navigation and interaction. While Vision-Language Models (VLMs) provide open-world semantic priors, they lack grounding in 3D geometry and temporal dynamics. Conversely, geometric perception captures structure and motion but remains semantically sparse. We propose SNOW (Scene Understanding with Open-World Knowledge), a training-free and backbone-agnostic framework for unified 4D scene understanding that integrates VLM-derived semantics with point cloud geometry and temporal consistency. SNOW processes synchronized RGB images and 3D point clouds, using HDBSCAN clustering to generate object-level proposals that guide SAM2-based segmentation. Each segmented region is encoded through our proposed Spatio-Temporal Tokenized Patch Encoding (STEP), producing multimodal tokens that capture localized semantic, geometric, and temporal attributes. These tokens are incrementally integrated into a 4D Scene Graph (4DSG), which serves as 4D prior for downstream reasoning. A lightweight SLAM backend anchors all STEP tokens spatially in the environment, providing the global reference alignment, and ensuring unambiguous spatial grounding across time. The resulting 4DSG forms a queryable, unified world model through which VLMs can directly interpret spatial scene structure and temporal dynamics. Experiments on a diverse set of benchmarks demonstrate that SNOW enables precise 4D scene understanding and spatially grounded inference, thereby setting new state-of-the-art performance in several settings, highlighting the importance of structured 4D priors for embodied reasoning and autonomous robotics.

Pinxin Liu, Haiyang Liu, Luchuan Song et al.

When humans speak, gestures help convey communicative intentions, such as adding emphasis or describing concepts. However, current co-speech gesture generation methods rely solely on superficial linguistic cues (e.g. speech audio or text transcripts), neglecting to understand and leverage the communicative intention that underpins human gestures. This results in outputs that are rhythmically synchronized with speech but are semantically shallow. To address this gap, we introduce Intentional-Gesture, a novel framework that casts gesture generation as an intention-reasoning task grounded in high-level communicative functions. First, we curate the InG dataset by augmenting BEAT-2 with gesture-intention annotations (i.e., text sentences summarizing intentions), which are automatically annotated using large vision-language models. Next, we introduce the Intentional Gesture Motion Tokenizer to leverage these intention annotations. It injects high-level communicative functions (e.g., intentions) into tokenized motion representations to enable intention-aware gesture synthesis that are both temporally aligned and semantically meaningful, achieving new state-of-the-art performance on the BEAT-2 benchmark. Our framework offers a modular foundation for expressive gesture generation in digital humans and embodied AI. Project Page: https://andypinxinliu.github.io/Intentional-Gesture

Filippos Bellos, Nam H. Nguyen, Jason J. Corso

Although LLMs have demonstrated remarkable capabilities in processing and generating textual data, their pre-trained vocabularies are ill-suited for capturing the nuanced temporal dynamics and patterns inherent in time series. The discrete, symbolic nature of natural language tokens, which these vocabularies are designed to represent, does not align well with the continuous, numerical nature of time series data. To address this fundamental limitation, we propose VITRO. Our method adapts textual inversion optimization from the vision-language domain in order to learn a new time series per-dataset vocabulary that bridges the gap between the discrete, semantic nature of natural language and the continuous, numerical nature of time series data. We show that learnable time series-specific pseudo-word embeddings represent time series data better than existing general language model vocabularies, with VITRO-enhanced methods achieving state-of-the-art performance in long-term forecasting across most datasets.

Filippos Bellos, Yayuan Li, Cary Shu et al.

Effective human-AI collaboration for physical task completion has significant potential in both everyday activities and professional domains. AI agents equipped with informative guidance can enhance human performance, but evaluating such collaboration remains challenging due to the complexity of human-in-the-loop interactions. In this work, we introduce an evaluation framework and a multimodal dataset of human-AI interactions designed to assess how AI guidance affects procedural task performance, error reduction and learning outcomes. Besides, we develop an augmented reality (AR)-equipped AI agent that provides interactive guidance in real-world tasks, from cooking to battlefield medicine. Through human studies, we share empirical insights into AI-assisted human performance and demonstrate that AI-assisted collaboration improves task completion.

Tin Stribor Sohn, Philipp Reis, Maximilian Dillitzer et al.

Multimodal large language models (MLLMs) hold the potential to enhance autonomous driving by combining domain-independent world knowledge with context-specific language guidance. Their integration into autonomous driving systems shows promising results in isolated proof-of-concept applications, while their performance is evaluated on selective singular aspects of perception, reasoning, or planning. To leverage their full potential a systematic framework for evaluating MLLMs in the context of autonomous driving is required. This paper proposes a holistic framework for a capability-driven evaluation of MLLMs in autonomous driving. The framework structures scenario understanding along the four core capability dimensions semantic, spatial, temporal, and physical. They are derived from the general requirements of autonomous driving systems, human driver cognition, and language-based reasoning. It further organises the domain into context layers, processing modalities, and downstream tasks such as language-based interaction and decision-making. To illustrate the framework's applicability, two exemplary traffic scenarios are analysed, grounding the proposed dimensions in realistic driving situations. The framework provides a foundation for the structured evaluation of MLLMs' potential for scenario understanding in autonomous driving.

Nathan Louis, Mahzad Khoshlessan, Jason J. Corso

Modeling humans in physical scenes is vital for understanding human-environment interactions for applications involving augmented reality or assessment of human actions from video (e.g. sports or physical rehabilitation). State-of-the-art literature begins with a 3D human pose, from monocular or multiple views, and uses this representation to ground the person within a 3D world space. While standard metrics for accuracy capture joint position errors, they do not consider physical plausibility of the 3D pose. This limitation has motivated researchers to propose other metrics evaluating jitter, floor penetration, and unbalanced postures. Yet, these approaches measure independent instances of errors and are not representative of balance or stability during motion. In this work, we propose measuring physical plausibility from within physics simulation. We introduce two metrics to capture the physical plausibility and stability of predicted 3D poses from any 3D Human Pose Estimation model. Using physics simulation, we discover correlations with existing plausibility metrics and measuring stability during motion. We evaluate and compare the performances of two state-of-the-art methods, a multi-view triangulated baseline, and ground truth 3D markers from the Human3.6m dataset.

Shane Storks, Itamar Bar-Yossef, Yayuan Li et al.

Procedural mistake detection (PMD) is a challenging problem of classifying whether a human user (observed through egocentric video) has successfully executed a task (specified by a procedural text). Despite significant recent efforts, machine performance in the wild remains nonviable, and the reasoning processes underlying this performance are opaque. As such, we extend PMD to require generating visual self-dialog rationales to inform decisions. Given the impressive, mature image understanding capabilities observed in recent vision-and-language models (VLMs), we curate a suitable benchmark dataset for PMD based on individual frames. As our reformulation enables unprecedented transparency, we leverage a natural language inference (NLI) model to formulate two automated metrics for the coherence of generated rationales. We establish baselines for this reframed task, showing that VLMs struggle off-the-shelf, but with some trade-offs, their accuracy, coherence, and efficiency can be improved by incorporating these metrics into common inference and fine-tuning methods. Lastly, our multi-faceted metrics visualize common outcomes, highlighting areas for further improvement.

Yayuan Li, Zhi Cao, Jason J. Corso

Despite the recent strides in video generation, state-of-the-art methods still struggle with elements of visual detail. One particularly challenging case is the class of videos in which the intricate motion of the hand coupled with a mostly stable and otherwise distracting environment is necessary to convey the execution of some complex action and its effects. To address these challenges, we introduce a new method for video generation that focuses on hand-centric actions. Our diffusion-based method incorporates two distinct innovations. First, we propose an automatic method to generate the motion area -- the region in the video in which the detailed activities occur -- guided by both the visual context and the action text prompt, rather than assuming this region can be provided manually as is now commonplace. Second, we introduce a critical Hand Refinement Loss to guide the diffusion model to focus on smooth and consistent hand poses. We evaluate our method on challenging augmented datasets based on EpicKitchens and Ego4D, demonstrating significant improvements over state-of-the-art methods in terms of action clarity, especially of the hand motion in the target region, across diverse environments and actions. Video results can be found in https://excitedbutter.github.io/project_page

Miaowei Wang, Qingxuan Yan, Zhi Cao et al.

Text-guided dynamic 3D character generation has advanced rapidly, yet producing high-quality motion that faithfully reflects rich textual descriptions remains challenging. Existing methods tend to generate limited sub-actions or incoherent motion due to fixed-length temporal inputs and discrete frame-wise representations that fail to capture rich motion semantics. We address these limitations by representing motion with continuous differentiable B-spline curves, enabling more effective motion generation without modifying the capabilities of the underlying generative model. Specifically, our closed-form, Laplacian-regularized B-spline solver efficiently compresses variable-length motion sequences into compact representations with a fixed number of control points. Further, we introduce a normal-fusion strategy for input shape adherence along with correspondence-aware and local-rigidity losses for motion-restoration quality. To train our model, we collate BIMO, a new dataset containing diverse variable-length 3D motion sequences with rich, high-quality text annotations. Extensive evaluations show that our feed-forward framework BiMotion generates more expressive, higher-quality, and better prompt-aligned motions than existing state-of-the-art methods, while also achieving faster generation. Our project page is at: https://wangmiaowei.github.io/BiMotion.github.io/.

Jing Bi, Filippos Bellos, Junjia Guo et al.

Test-time thinking (that is, generating explicit intermediate reasoning chains) is known to boost performance in large language models and has recently shown strong gains for large vision language models (LVLMs). However, despite these promising results, there is still no systematic analysis of how thinking actually affects visual reasoning. We provide the first such analysis with a large scale, controlled comparison of thinking for LVLMs, evaluating ten variants from the InternVL3.5 and Qwen3-VL families on MMMU-val under generous token budgets and multi pass decoding. We show that more thinking is not always better; long chains often yield long wrong trajectories that ignore the image and underperform the same models run in standard instruct mode. A deeper analysis reveals that certain short lookback phrases, which explicitly refer back to the image, are strongly enriched in successful trajectories and correlate with better visual grounding. Building on this insight, we propose uncertainty guided lookback, a training free decoding strategy that combines an uncertainty signal with adaptive lookback prompts and breadth search. Our method improves overall MMMU performance, delivers the largest gains in categories where standard thinking is weak, and outperforms several strong decoding baselines, setting a new state of the art under fixed model families and token budgets. We further show that this decoding strategy generalizes, yielding consistent improvements on five additional benchmarks, including two broad multimodal suites and math focused visual reasoning datasets.

Yayuan Li, Aadit Jain, Filippos Bellos et al.

We introduce Mistake Attribution (MATT), a task for fine-grained understanding of human mistakes in egocentric video. Unlike prior mistake understanding work, which lacks fine-grained output, MATT concretely attributes mistakes to the input instruction text or the attempt video. MATT determines what part of the instruction is violated (semantic role), when the deviation becomes irreversible (the Point-of-No-Return, PNR), and where the mistake appears in the PNR frame. We develop MisEngine, a data engine that automatically constructs attribution-rich mistake samples from existing datasets and inherits their annotations. Applied to large egocentric corpora, MisEngine yields EPIC-KITCHENS-M and Ego4D-M, two datasets that are up to two orders of magnitude larger than prior mistake datasets. We then present MisFormer, a unified attention-based model for mistake attribution across semantic (what), temporal (when), and spatial (where) dimensions, trained using MisEngine supervision. Experiments on our new datasets and prior benchmarks show that MisFormer outperforms strong video-language, temporal localization, hand-object interaction, and mistake-detection baselines.

Brent A. Griffin, Manushree Gangwar, Jacob Sela et al.

Great labels make great models. However, traditional labeling approaches for tasks like object detection have substantial costs at scale. Furthermore, alternatives to fully-supervised object detection either lose functionality or require larger models with prohibitive computational costs for inference at scale. To that end, this paper addresses the problem of training standard object detection models without any ground truth labels. Instead, we configure previously-trained vision-language foundation models to generate application-specific pseudo "ground truth" labels. These auto-generated labels directly integrate with existing model training frameworks, and we subsequently train lightweight detection models that are computationally efficient. In this way, we avoid the costs of traditional labeling, leverage the knowledge of vision-language models, and keep the efficiency of lightweight models for practical application. We perform exhaustive experiments across multiple labeling configurations, downstream inference models, and datasets to establish best practices and set an extensive auto-labeling benchmark. From our results, we find that our approach is a viable alternative to standard labeling in that it maintains competitive performance on multiple datasets and substantially reduces labeling time and costs.

Stephan J. Lemmer, Jason J. Corso

Many AI systems integrate sensor inputs, world knowledge, and human-provided information to perform inference. While such systems often treat the human input as flawless, humans are better thought of as hazy oracles whose input may be ambiguous or outside of the AI system's understanding. In such situations it makes sense for the AI system to defer its inference while it disambiguates the human-provided information by, for example, asking the human to rephrase the query. Though this approach has been considered in the past, current work is typically limited to application-specific methods and non-standardized human experiments. We instead introduce and formalize a general notion of deferred inference. Using this formulation, we then propose a novel evaluation centered around the Deferred Error Volume (DEV) metric, which explicitly considers the tradeoff between error reduction and the additional human effort required to achieve it. We demonstrate this new formalization and an innovative deferred inference method on the disparate tasks of Single-Target Video Object Tracking and Referring Expression Comprehension, ultimately reducing error by up to 48% without any change to the underlying model or its parameters.

Brent A. Griffin, Jason J. Corso

This paper addresses the problem of learning to estimate the depth of detected objects given some measurement of camera motion (e.g., from robot kinematics or vehicle odometry). We achieve this by 1) designing a recurrent neural network (DBox) that estimates the depth of objects using a generalized representation of bounding boxes and uncalibrated camera movement and 2) introducing the Object Depth via Motion and Detection Dataset (ODMD). ODMD training data are extensible and configurable, and the ODMD benchmark includes 21,600 examples across four validation and test sets. These sets include mobile robot experiments using an end-effector camera to locate objects from the YCB dataset and examples with perturbations added to camera motion or bounding box data. In addition to the ODMD benchmark, we evaluate DBox in other monocular application domains, achieving state-of-the-art results on existing driving and robotics benchmarks and estimating the depth of objects using a camera phone.

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.

Kyle Min, Jason J. Corso

It is well known that human gaze carries significant information about visual attention. However, there are three main difficulties in incorporating the gaze data in an attention mechanism of deep neural networks: 1) the gaze fixation points are likely to have measurement errors due to blinking and rapid eye movements; 2) it is unclear when and how much the gaze data is correlated with visual attention; and 3) gaze data is not always available in many real-world situations. In this work, we introduce an effective probabilistic approach to integrate human gaze into spatiotemporal attention for egocentric activity recognition. Specifically, we represent the locations of gaze fixation points as structured discrete latent variables to model their uncertainties. In addition, we model the distribution of gaze fixations using a variational method. The gaze distribution is learned during the training process so that the ground-truth annotations of gaze locations are no longer needed in testing situations since they are predicted from the learned gaze distribution. The predicted gaze locations are used to provide informative attentional cues to improve the recognition performance. Our method outperforms all the previous state-of-the-art approaches on EGTEA, which is a large-scale dataset for egocentric activity recognition provided with gaze measurements. We also perform an ablation study and qualitative analysis to demonstrate that our attention mechanism is effective.

Shurjo Banerjee, Jesse Thomason, Jason J. Corso

Autonomous robot systems for applications from search and rescue to assistive guidance should be able to engage in natural language dialog with people. To study such cooperative communication, we introduce Robot Simultaneous Localization and Mapping with Natural Language (RobotSlang), a benchmark of 169 natural language dialogs between a human Driver controlling a robot and a human Commander providing guidance towards navigation goals. In each trial, the pair first cooperates to localize the robot on a global map visible to the Commander, then the Driver follows Commander instructions to move the robot to a sequence of target objects. We introduce a Localization from Dialog History (LDH) and a Navigation from Dialog History (NDH) task where a learned agent is given dialog and visual observations from the robot platform as input and must localize in the global map or navigate towards the next target object, respectively. RobotSlang is comprised of nearly 5k utterances and over 1k minutes of robot camera and control streams. We present an initial model for the NDH task, and show that an agent trained in simulation can follow the RobotSlang dialog-based navigation instructions for controlling a physical robot platform. Code and data are available at https://umrobotslang.github.io/.

Stephan J. Lemmer, Jason J. Corso

Many vision tasks use secondary information at inference time -- a seed -- to assist a computer vision model in solving a problem. For example, an initial bounding box is needed to initialize visual object tracking. To date, all such work makes the assumption that the seed is a good one. However, in practice, from crowdsourcing to noisy automated seeds, this is often not the case. We hence propose the problem of seed rejection -- determining whether to reject a seed based on the expected performance degradation when it is provided in place of a gold-standard seed. We provide a formal definition to this problem, and focus on two meaningful subgoals: understanding causes of error and understanding the model's response to noisy seeds conditioned on the primary input. With these goals in mind, we propose a novel training method and evaluation metrics for the seed rejection problem. We then use seeded versions of the viewpoint estimation and fine-grained classification tasks to evaluate these contributions. In these experiments, we show our method can reduce the number of seeds that need to be reviewed for a target performance by over 23% compared to strong baselines.

Duygu Sarikaya, Jason J. Corso, Khurshid A. Guru

Video understanding of robot-assisted surgery (RAS) videos is an active research area. Modeling the gestures and skill level of surgeons presents an interesting problem. The insights drawn may be applied in effective skill acquisition, objective skill assessment, real-time feedback, and human-robot collaborative surgeries. We propose a solution to the tool detection and localization open problem in RAS video understanding, using a strictly computer vision approach and the recent advances of deep learning. We propose an architecture using multimodal convolutional neural networks for fast detection and localization of tools in RAS videos. To our knowledge, this approach will be the first to incorporate deep neural networks for tool detection and localization in RAS videos. Our architecture applies a Region Proposal Network (RPN), and a multi-modal two stream convolutional network for object detection, to jointly predict objectness and localization on a fusion of image and temporal motion cues. Our results with an Average Precision (AP) of 91% and a mean computation time of 0.1 seconds per test frame detection indicate that our study is superior to conventionally used methods for medical imaging while also emphasizing the benefits of using RPN for precision and efficiency. We also introduce a new dataset, ATLAS Dione, for RAS video understanding. Our dataset provides video data of ten surgeons from Roswell Park Cancer Institute (RPCI) (Buffalo, NY) performing six different surgical tasks on the daVinci Surgical System (dVSS R ) with annotations of robotic tools per frame.

Kyle Min, Jason J. Corso

Temporally localizing activities within untrimmed videos has been extensively studied in recent years. Despite recent advances, existing methods for weakly-supervised temporal activity localization struggle to recognize when an activity is not occurring. To address this issue, we propose a novel method named A2CL-PT. Two triplets of the feature space are considered in our approach: one triplet is used to learn discriminative features for each activity class, and the other one is used to distinguish the features where no activity occurs (i.e. background features) from activity-related features for each video. To further improve the performance, we build our network using two parallel branches which operate in an adversarial way: the first branch localizes the most salient activities of a video and the second one finds other supplementary activities from non-localized parts of the video. Extensive experiments performed on THUMOS14 and ActivityNet datasets demonstrate that our proposed method is effective. Specifically, the average mAP of IoU thresholds from 0.1 to 0.9 on the THUMOS14 dataset is significantly improved from 27.9% to 30.0%.

Brent A. Griffin, Jason J. Corso

Video object segmentation, i.e., the separation of a target object from background in video, has made significant progress on real and challenging videos in recent years. To leverage this progress in 3D applications, this paper addresses the problem of learning to estimate the depth of segmented objects given some measurement of camera motion (e.g., from robot kinematics or vehicle odometry). We achieve this by, first, introducing a diverse, extensible dataset and, second, designing a novel deep network that estimates the depth of objects using only segmentation masks and uncalibrated camera movement. Our data-generation framework creates artificial object segmentations that are scaled for changes in distance between the camera and object, and our network learns to estimate object depth even with segmentation errors. We demonstrate our approach across domains using a robot camera to locate objects from the YCB dataset and a vehicle camera to locate obstacles while driving.

Madan Ravi Ganesh, Dawsin Blanchard, Jason J. Corso et al.

In general, deep neural network (DNN) pruning methods fall into two categories: 1) Weight-based deterministic constraints, and 2) Probabilistic frameworks. While each approach has its merits and limitations there are a set of common practical issues such as, trial-and-error to analyze sensitivity and hyper-parameters to prune DNNs, which plague them both. In this work, we propose a new single-shot, fully automated pruning algorithm called Slimming Neural networks using Adaptive Connectivity Scores (SNACS). Our proposed approach combines a probabilistic pruning framework with constraints on the underlying weight matrices, via a novel connectivity measure, at multiple levels to capitalize on the strengths of both approaches while solving their deficiencies. In \alg{}, we propose a fast hash-based estimator of Adaptive Conditional Mutual Information (ACMI), that uses a weight-based scaling criterion, to evaluate the connectivity between filters and prune unimportant ones. To automatically determine the limit up to which a layer can be pruned, we propose a set of operating constraints that jointly define the upper pruning percentage limits across all the layers in a deep network. Finally, we define a novel sensitivity criterion for filters that measures the strength of their contributions to the succeeding layer and highlights critical filters that need to be completely protected from pruning. Through our experimental validation we show that SNACS is faster by over 17x the nearest comparable method and is the state of the art single-shot pruning method across three standard Dataset-DNN pruning benchmarks: CIFAR10-VGG16, CIFAR10-ResNet56 and ILSVRC2012-ResNet50.

Mohamed El Banani, Jason J. Corso, David F. Fouhey

The goal of this paper is to estimate the viewpoint for a novel object. Standard viewpoint estimation approaches generally fail on this task due to their reliance on a 3D model for alignment or large amounts of class-specific training data and their corresponding canonical pose. We overcome those limitations by learning a reconstruct and align approach. Our key insight is that although we do not have an explicit 3D model or a predefined canonical pose, we can still learn to estimate the object's shape in the viewer's frame and then use an image to provide our reference model or canonical pose. In particular, we propose learning two networks: the first maps images to a 3D geometry-aware feature bottleneck and is trained via an image-to-image translation loss; the second learns whether two instances of features are aligned. At test time, our model finds the relative transformation that best aligns the bottleneck features of our test image to a reference image. We evaluate our method on novel object viewpoint estimation by generalizing across different datasets, analyzing the impact of our different modules, and providing a qualitative analysis of the learned features to identify what representations are being learnt for alignment.

Madan Ravi Ganesh, Jason J. Corso, Salimeh Yasaei Sekeh

Most approaches to deep neural network compression via pruning either evaluate a filter's importance using its weights or optimize an alternative objective function with sparsity constraints. While these methods offer a useful way to approximate contributions from similar filters, they often either ignore the dependency between layers or solve a more difficult optimization objective than standard cross-entropy. Our method, Mutual Information-based Neuron Trimming (MINT), approaches deep compression via pruning by enforcing sparsity based on the strength of the relationship between filters of adjacent layers, across every pair of layers. The relationship is calculated using conditional geometric mutual information which evaluates the amount of similar information exchanged between the filters using a graph-based criterion. When pruning a network, we ensure that retained filters contribute the majority of the information towards succeeding layers which ensures high performance. Our novel approach outperforms existing state-of-the-art compression-via-pruning methods on the standard benchmarks for this task: MNIST, CIFAR-10, and ILSVRC2012, across a variety of network architectures. In addition, we discuss our observations of a common denominator between our pruning methodology's response to adversarial attacks and calibration statistics when compared to the original network.

Madan Ravi Ganesh, Jason J. Corso

Like humans, deep networks have been shown to learn better when samples are organized and introduced in a meaningful order or curriculum. Conventional curriculum learning schemes introduce samples in their order of difficulty. This forces models to begin learning from a subset of the available data while adding the external overhead of evaluating the difficulty of samples. In this work, we propose Learning with Incremental Labels and Adaptive Compensation (LILAC), a two-phase method that incrementally increases the number of unique output labels rather than the difficulty of samples while consistently using the entire dataset throughout training. In the first phase, Incremental Label Introduction, we partition data into mutually exclusive subsets, one that contains a subset of the ground-truth labels and another that contains the remaining data attached to a pseudo-label. Throughout the training process, we recursively reveal unseen ground-truth labels in fixed increments until all the labels are known to the model. In the second phase, Adaptive Compensation, we optimize the loss function using altered target vectors of previously misclassified samples. The target vectors of such samples are modified to a smoother distribution to help models learn better. On evaluating across three standard image benchmarks, CIFAR-10, CIFAR-100, and STL-10, we show that LILAC outperforms all comparable baselines. Further, we detail the importance of pacing the introduction of new labels to a model as well as the impact of using a smooth target vector.

Ryan Szeto, Mostafa El-Khamy, Jungwon Lee et al.

Video-to-video translation is more difficult than image-to-image translation due to the temporal consistency problem that, if unaddressed, leads to distracting flickering effects. Although video models designed from scratch produce temporally consistent results, training them to match the vast visual knowledge captured by image models requires an intractable number of videos. To combine the benefits of image and video models, we propose an image-to-video model transfer method called Hyperconsistency (HyperCon) that transforms any well-trained image model into a temporally consistent video model without fine-tuning. HyperCon works by translating a temporally interpolated video frame-wise and then aggregating over temporally localized windows on the interpolated video. It handles both masked and unmasked inputs, enabling support for even more video-to-video translation tasks than prior image-to-video model transfer techniques. We demonstrate HyperCon on video style transfer and inpainting, where it performs favorably compared to prior state-of-the-art methods without training on a single stylized or incomplete video. Our project website is available at https://ryanszeto.com/projects/hypercon .

Salimeh Yasaei Sekeh, Madan Ravi Ganesh, Shurjo Banerjee et al.

Online Streaming Feature Selection (OSFS) is a sequential learning problem where individual features across all samples are made available to algorithms in a streaming fashion. In this work, firstly, we assert that OSFS's main assumption of having data from all the samples available at runtime is unrealistic and introduce a new setting where features and samples are streamed concurrently called OSFS with Streaming Samples (OSFS-SS). Secondly, the primary OSFS method, SAOLA utilizes an unbounded mutual information measure and requires multiple comparison steps between the stored and incoming feature sets to evaluate a feature's importance. We introduce Geometric Online Adaption, an algorithm that requires relatively less feature comparison steps and uses a bounded conditional geometric dependency measure. Our algorithm outperforms several OSFS baselines including SAOLA on a variety of datasets. We also extend SAOLA to work in the OSFS-SS setting and show that GOA continues to achieve the best results. Thirdly, the current paradigm of the OSFS algorithm comparison is flawed. Algorithms are measured by comparing the number of features used and the accuracy obtained by the learner, two properties that are fundamentally at odds with one another. Without fixing a limit on either of these properties, the qualities of features obtained by different algorithms are incomparable. We try to rectify this inconsistency by fixing the maximum number of features available to the learner and comparing algorithms in terms of their accuracy. Additionally, we characterize the behaviour of SAOLA and GOA on feature sets derived from popular deep convolutional featurizers.

Kyle Min, Jason J. Corso

TASED-Net is a 3D fully-convolutional network architecture for video saliency detection. It consists of two building blocks: first, the encoder network extracts low-resolution spatiotemporal features from an input clip of several consecutive frames, and then the following prediction network decodes the encoded features spatially while aggregating all the temporal information. As a result, a single prediction map is produced from an input clip of multiple frames. Frame-wise saliency maps can be predicted by applying TASED-Net in a sliding-window fashion to a video. The proposed approach assumes that the saliency map of any frame can be predicted by considering a limited number of past frames. The results of our extensive experiments on video saliency detection validate this assumption and demonstrate that our fully-convolutional model with temporal aggregation method is effective. TASED-Net significantly outperforms previous state-of-the-art approaches on all three major large-scale datasets of video saliency detection: DHF1K, Hollywood2, and UCFSports. After analyzing the results qualitatively, we observe that our model is especially better at attending to salient moving objects.

Victoria Florence, Jason J. Corso, Brent Griffin

To be effective in unstructured and changing environments, robots must learn to recognize new objects. Deep learning has enabled rapid progress for object detection and segmentation in computer vision; however, this progress comes at the price of human annotators labeling many training examples. This paper addresses the problem of extending learning-based segmentation methods to robotics applications where annotated training data is not available. Our method enables pixelwise segmentation of grasped objects. We factor the problem of segmenting the object from the background into two sub-problems: (1) segmenting the robot manipulator and object from the background and (2) segmenting the object from the manipulator. We propose a kinematics-based foreground segmentation technique to solve (1). To solve (2), we train a self-recognition network that segments the robot manipulator. We train this network without human supervision, leveraging our foreground segmentation technique from (1) to label a training set of images containing the robot manipulator without a grasped object. We demonstrate experimentally that our method outperforms state-of-the-art adaptable in-hand object segmentation. We also show that a training set composed of automatically labelled images of grasped objects improves segmentation performance on a test set of images of the same objects in the environment.

Brent A. Griffin, Jason J. Corso

Semi-supervised video object segmentation has made significant progress on real and challenging videos in recent years. The current paradigm for segmentation methods and benchmark datasets is to segment objects in video provided a single annotation in the first frame. However, we find that segmentation performance across the entire video varies dramatically when selecting an alternative frame for annotation. This paper address the problem of learning to suggest the single best frame across the video for user annotation-this is, in fact, never the first frame of video. We achieve this by introducing BubbleNets, a novel deep sorting network that learns to select frames using a performance-based loss function that enables the conversion of expansive amounts of training examples from already existing datasets. Using BubbleNets, we are able to achieve an 11% relative improvement in segmentation performance on the DAVIS benchmark without any changes to the underlying method of segmentation.

Brent A. Griffin, Victoria Florence, Jason J. Corso

To be useful in everyday environments, robots must be able to identify and locate real-world objects. In recent years, video object segmentation has made significant progress on densely separating such objects from background in real and challenging videos. Building off of this progress, this paper addresses the problem of identifying generic objects and locating them in 3D using a mobile robot with an RGB camera. We achieve this by, first, introducing a video object segmentation-based approach to visual servo control and active perception and, second, developing a new Hadamard-Broyden update formulation. Our segmentation-based methods are simple but effective, and our update formulation lets a robot quickly learn the relationship between actuators and visual features without any camera calibration. We validate our approach in experiments by learning a variety of actuator-camera configurations on a mobile HSR robot, which subsequently identifies, locates, and grasps objects from the YCB dataset and tracks people and other dynamic articulated objects in real-time.

Hao Tang, Xinya Chen, Wei Wang et al.

Facial attributes are important since they provide a detailed description and determine the visual appearance of human faces. In this paper, we aim at converting a face image to a sketch while simultaneously generating facial attributes. To this end, we propose a novel Attribute-Guided Sketch Generative Adversarial Network (ASGAN) which is an end-to-end framework and contains two pairs of generators and discriminators, one of which is used to generate faces with attributes while the other one is employed for image-to-sketch translation. The two generators form a W-shaped network (W-net) and they are trained jointly with a weight-sharing constraint. Additionally, we also propose two novel discriminators, the residual one focusing on attribute generation and the triplex one helping to generate realistic looking sketches. To validate our model, we have created a new large dataset with 8,804 images, named the Attribute Face Photo & Sketch (AFPS) dataset which is the first dataset containing attributes associated to face sketch images. The experimental results demonstrate that the proposed network (i) generates more photo-realistic faces with sharper facial attributes than baselines and (ii) has good generalization capability on different generative tasks.

Abhishek Venkataraman, Brent Griffin, Jason J. Corso

To be useful in everyday environments, robots must be able to observe and learn about objects. Recent datasets enable progress for classifying data into known object categories; however, it is unclear how to collect reliable object data when operating in cluttered, partially-observable environments. In this paper, we address the problem of building complete 3D models for real-world objects using a robot platform, which can remove objects from clutter for better classification. Furthermore, we are able to learn entirely new object categories as they are encountered, enabling the robot to classify previously unidentifiable objects during future interactions. We build models of grasped objects using simultaneous manipulation and observation, and we guide the processing of visual data using a kinematic description of the robot to combine observations from different view-points and remove background noise. To test our framework, we use a mobile manipulation robot equipped with an RGBD camera to build voxelized representations of unknown objects and then classify them into new categories. We then have the robot remove objects from clutter to manipulate, observe, and classify them in real-time.

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.