Large Language Models (LLMs) have significantly impacted the field of Math Word Problems (MWPs), transforming how these problems are approached and solved, particularly in educational contexts.However, existing evaluations often focus on final accuracy, neglecting the critical aspect of reasoning capabilities.This work addresses that gap by evaluating LLMs' abilities to detect and correct reasoning mistakes.We present a novel dataset, MWP-MISTAKE, containing MWPs with both correct and incorrect reasoning steps generated through rule-based methods and smaller language models.Our comprehensive benchmarking of state-of-the-art models such as GPT-4o and GPT4 uncovers important insights into their strengths and limitations.While GPT-4o excels in mistake detection and rectification, gaps remain, particularly in handling complex datasets and novel problems.Additionally, we identify concerns with data contamination and memorization, which affect LLM reliability in real-world applications.While OpenAI' O1 model demonstrates 90% accuracy in reasoning and final answers on complex tasks, it remains weak in mistake detection.Our findings highlight the need for improved reasoning evaluations and suggest ways to enhance LLM generalization and robustness in math problemsolving.Question: What is the product of the coordinates of the midpoint of a line segment with endpoints at (1,1) and (-7,5)? Reasoning Step:The midpoint of a line segment is located at the point (h,k), where h = (x1 + x2)/2 and k = (y1 + y2)/2.In this case, the endpoints of the line segment are (1,1) and (-7,5).So, we can find the midpoint by calculating h = (1 + (-7))/2 = 6 and k = (1 + 5)/2 = 3.Therefore, the product of the coordinates of the midpoint is hk = 6 * 3 = 18.Reasoning chain Correct (Yes/No): No Corrected reasoning chain or NA: The midpoint of a line segment is located at the point (h,k), where h = (x1 + x2 )/ 2 and k = (y1 + y2)/2.In this case, the endpoints of the line segment are (1,1) and (-7,5).So, we can find the midpoint by calculating: h = (1 + (-7))/2 = -6/2 = -3 k = (1 + 5)/2 = 6/2 = 3 Therefore, the product of the coordinates of the midpoint is: hk = -3 * 3 = -9 Final answer (just the number): -9 Reasoning chain Correct (Yes/No): Yes Correct Reasoning Chain or NA: NA Final answer (just the number): 18 Model Input Open AI Models GPT-4o GPT 3.5 Turbo You are provided with a mathematical question and a step-by-step solution along with it.The solution might have some mistakes.Identify if the solution is correct or incorrect.If the solution is correct, output the final answer with the help of the solution provided.If the solution is incorrect, correct the existing solution and determine the final answer with the help of the corrected solution.

Despite advancements in multimodal large language models (MLLMs), current approaches struggle in medium-to-long video understanding due to frame and context length limitations. As a result, these models often depend on frame sampling, which risks missing key information over time and lacks task-specific relevance. To address these challenges, we introduce HierarQ, a task-aware hierarchical Q-Former based framework that sequentially processes frames to bypass the need for frame sampling, while avoiding LLM’s context length limitations. We introduce a lightweight two-stream language-guided feature modulator to incorporate task awareness in video understanding, with the entity stream capturing frame-level object information within a short context and the scene stream identifying their broader interactions over longer period of time. Each stream is supported by dedicated memory banks which enables our proposed Hierarchical Querying transformer (HierarQ) to effectively capture short and long-term context. Extensive evaluations on 10 video benchmarks across video understanding, question answering, and captioning tasks demonstrate HierarQ’s state-of-the-art performance across most datasets, proving its robustness and efficiency for comprehensive video analysis.

Existing text-to-audio (TTA) generation methods have neither systematically explored audio event relation modeling, nor proposed any new framework to enhance this capability.In this work, we systematically study audio event relation modeling in TTA generation models.We first establish a benchmark for this task by: (1) proposing a comprehensive relation corpus covering all potential relations in real-world scenarios; (2) introducing a new audio event corpus encompassing commonly heard audios; and (3) proposing new evaluation metrics to assess audio event relation modeling from various perspectives.Furthermore, we propose a gated prompt tuning strategy that improves existing TTA models' relation modeling capability with negligible extra parameters.Specifically, we introduce learnable relation and event prompt that append to the text prompt before feeding to existing TTA models 1 .

An embodied AI assistant operating on egocentric video must integrate spatial cues across time - for instance, determining where an object A, glimpsed a few moments ago lies relative to an object B encountered later. We introduce Disjoint-3DQA , a generative QA benchmark that evaluates this ability of VLMs by posing questions about object pairs that are not co-visible in the same frame. We evaluated seven state-of-the-art VLMs and found that models lag behind human performance by 28%, with steeper declines in accuracy (60% → 30 %) as the temporal gap widens. Our analysis further reveals that providing trajectories or bird’s-eye-view projections to VLMs results in only marginal improvements, whereas providing oracle 3D coordinates leads to a substantial 20% performance increase. This highlights a core bottleneck of multi-frame VLMs in constructing and maintaining 3D scene representations over time from visual signals. Disjoint-3DQA therefore sets a clear, measurable challenge for long-horizon spatial reasoning and aims to catalyze future research at the intersection of vision, language, and embodied AI.

With models getting stronger, evaluations have grown more complex, testing multiple skills in one benchmark and even in the same instance at once. However, skill-wise performance is obscured when inspecting aggregate accuracy, under-utilizing the rich signal modern benchmarks contain. We propose an automatic approach to recover the underlying skills relevant for any evaluation instance, by way of inspecting model-generated {\em rationales}. After validating the relevance of rationale-parsed skills and inferring skills for $46$k instances over $12$ benchmarks, we observe many skills to be common across benchmarks, resulting in the curation of hundreds of \emph{skill-slices} (i.e. sets of instances testing a common skill). Inspecting accuracy over these slices yields novel insights on model trade-offs: e.g., compared to GPT-4o and Claude 3.5 Sonnet, on average, Gemini 1.5 Pro is $18\%$ more accurate in \emph{computing molar mass}, but $19\\%$ less accurate in \emph{applying constitutional law}, despite the overall accuracies of the three models differing by a mere $0.4\\%$. Furthermore, we demonstrate the practical utility of our approach by showing that insights derived from skill slice analysis can generalize to held-out instances: when routing each instance to the model strongest on the relevant skills, we see a $3\\%$ accuracy improvement over our $12$ dataset corpus. Our skill-slices and framework open a new avenue in model evaluation, leveraging skill-specific analyses to unlock a more granular and actionable understanding of model capabilities.

The popularization of Text-to-Image (T2I) diffusion models enables the generation of high-quality images from text descriptions. However, generating diverse customized images with reference visual attributes remains challenging. This work focuses on personalizing T2I diffusion models at a more abstract concept or category level, adapting commonalities from a set of reference images while creating new instances with sufficient variations. We introduce a solution that allows a pretrained T2I diffusion model to learn a set of soft prompts, enabling the generation of novel images by sampling prompts from the learned distribution. These prompts offer text-guided editing capabilities and additional flexibility in controlling variation and mixing between multiple distributions. We also show the adaptability of the learned prompt distribution to other tasks, such as text-to-3D. Finally we demonstrate effectiveness of our approach through quantitative analysis including automatic evaluation and human assessment.

Modern video generation models like Sora have achieved remarkable success in producing high-quality videos. However, a significant limitation is their inability to offer interactive control to users, a feature that promises to open up unprecedented applications and creativity. In this work, we introduce the first solution to equip diffusion-based video generation models with spatio-temporal control. We present PEEKABOO, a novel masked attention module, which seamlessly integrates with current video generation models offering control without the need for additional training or inference overhead. To facilitate future research, we also introduce a comprehensive benchmark for interactive video generation. This benchmark offers a standardized framework for the community to assess the efficacy of emerging interactive video generation models. Our extensive qualitative and quantitative assessments reveal that PEEKABOO achieves up to a 3.8x improvement in mIoU over baseline models, all while maintaining the same latency. Code and benchmark are available on the webpage.

Large language models (LLMs) and vision-language models (VLMs) have demonstrated remarkable performance across a wide range of tasks and domains. Despite this promise, spatial understanding and reasoning—a fundamental component of human cognition—remains under-explored. We propose SpatialEval, a novel benchmark that covers diverse aspects of spatial reasoning such as relationship understanding, navigation, and counting. We conduct a comprehensive evaluation of competitive language and vision-language models. Our findings reveal several counter-intuitive insights that have been overlooked in the literature: (1) Spatial reasoning poses significant challenges where competitive models can fall behind random guessing; (2) Despite additional visual input, VLMs often under-perform compared to their LLM counterparts; (3) When both textual and visual information is available, multi-modal language models become less reliant on visual information if sufficient textual clues are provided. Additionally, we demonstrate that leveraging redundancy between vision and text can significantly enhance model performance. We hope our study will inform the development of multimodal models to improve spatial intelligence and further close the gap with human intelligence. Our code is available at https://github.com/jiayuww/SpatialEval.

We have seen a great progress in video action recognition in recent years. There are several models based on convolutional neural network (CNN) and some recent transformer based approaches which provide top performance on existing benchmarks. In this work, we perform a large-scale robustness analysis of these existing models for video action recognition. We focus on robustness against real-world distribution shift perturbations instead of adversarial perturbations. We propose four different benchmark datasets, HMDB51-P, UCF101-P, Kinetics400-P, and SSv2-P to perform this analysis. We study robustness of six state-of-the-art action recognition models against 90 different perturbations. The study reveals some interesting findings, 1) transformer based models are consistently more robust compared to CNN based models, 2) Pretraining improves robustness for Transformer based models more than CNN based models, and 3) All of the studied models are robust to temporal perturbations for all datasets but SSv2; suggesting the importance of temporal information for action recognition varies based on the dataset and activities. Next, we study the role of augmentations in model robustness and present a real-world dataset, UCF101-DS, which contains realistic distribution shifts, to further validate some of these findings. We believe this study will serve as a benchmark for future research in robust video action recognition11More details available at bit.1y/3TJLMUF..

A recent trend in deep learning algorithms has been towards training large scale models, having high parameter count and trained on big dataset. However, robustness of such large scale models towards real-world settings is still a less-explored topic. In this work, we first benchmark the performance of these models under different perturbations and datasets thereby representing real-world shifts, and highlight their degrading performance under these shifts. We then discuss on how complete model fine-tuning based existing robustification schemes might not be a scalable option given very large scale networks and can also lead them to forget some of the desired characterstics. Finally, we propose a simple and cost-effective method to solve this problem, inspired by knowledge transfer literature. It involves robustifying smaller models, at a lower computation cost, and then use them as teachers to tune a fraction of these large scale networks, reducing the overall computational overhead. We evaluate our proposed method under various vision perturbations including ImageNet-C,R,S,A datasets and also for transfer learning, zero-shot evaluation setups on different datasets. Benchmark results show that our method is able to induce robustness to these large scale models efficiently, requiring significantly lower time and also preserves the transfer learning, zero-shot properties of the original model which none of the existing methods are able to achieve.

It is very time consuming to create datasets for training computer vision models. An emerging alternative is to use synthetic data, but if the synthetic data is not similar enough to the real data, the performance is typically below that of training with real data. Thus using synthetic data still requires a large amount of time, money, and skill as one needs to author the data carefully. In this paper, we seek to understand which aspects of this authoring process are most critical. We present an analysis of which factors of variation between simulated and real data are most important. We capture images of YCB objects to create a novel YCB-Real dataset. We then create a novel synthetic "digital twin" dataset, YCB-Synthetic, which matches the YCB-Real dataset and includes variety of artifacts added to the synthetic data. We study the affects of these artifacts on our dataset and two existing published datasets on two different computer vision tasks: object detection and instance segmentation. We provide an analysis of the cost-benefit trade-offs between artist time for fixing artifacts and trained model accuracy. We plan to release this dataset (images and 3D assets) so they can be further used by the community. Link to dataset1

In this work, we study the effect of occlusion on video action recognition. Tofacilitate this study, we propose three benchmark datasets and experiment withseven different video action recognition models. These datasets include two synthetic benchmarks, UCF-101-O and K-400-O, which enabled understanding the effects of fundamental properties of occlusion via controlled experiments. We also propose a real-world occlusion dataset, UCF-101-Y-OCC, which helps in further validating the findings of this study. We find several interesting insights such as 1) transformers are more robust than CNN counterparts, 2) pretraining make modelsrobust against occlusions, and 3) augmentation helps, but does not generalize well to real-world occlusions. In addition, we propose a simple transformer based compositional model, termed as CTx-Net, which generalizes well under this distribution shift. We observe that CTx-Net outperforms models which are trained using occlusions as augmentation, performing significantly better under natural occlusions. We believe this benchmark will open up interesting future research in robust video action recognition

Construction of a universal detector poses a crucial question: How can we most effectively train a model on a large mixture of datasets? The answer lies in learning dataset-specific features and ensembling their knowledge but do all this in a single model. Previous methods achieve this by having separate detection heads on a common backbone but that results in a significant increase in parameters. In this work, we present Mixture-of-Experts as a solution, highlighting that MoE are much more than a scalability tool. We propose Dataset-Aware Mixture-of-Experts, DAMEX where we train the experts to become an `expert' of a dataset by learning to route each dataset tokens to its mapped expert. Experiments on Universal Object-Detection Benchmark show that we outperform the existing state-of-the-art by average +10.2 AP score and improve over our non-MoE baseline by average +2.0 AP score. We also observe consistent gains while mixing datasets with (1) limited availability, (2) disparate domains and (3) divergent label sets. Further, we qualitatively show that DAMEX is robust against expert representation collapse. Code is available at https://github.com/jinga-lala/DAMEX

This paper explores the impact of occlusions in video action detection. We facilitatethis study by introducing five new benchmark datasets namely O-UCF and O-JHMDB consisting of synthetically controlled static/dynamic occlusions, OVIS-UCF and OVIS-JHMDB consisting of occlusions with realistic motions and Real-OUCF for occlusions in realistic-world scenarios. We formally confirm an intuitiveexpectation: existing models suffer a lot as occlusion severity is increased andexhibit different behaviours when occluders are static vs when they are moving.We discover several intriguing phenomenon emerging in neural nets: 1) transformerscan naturally outperform CNN models which might have even used occlusion as aform of data augmentation during training 2) incorporating symbolic-componentslike capsules to such backbones allows them to bind to occluders never even seenduring training and 3) Islands of agreement (similar to the ones hypothesized inHinton et Al’s GLOM) can emerge in realistic images/videos without instance-levelsupervision, distillation or contrastive-based objectives(eg. video-textual training).Such emergent properties allow us to derive simple yet effective training recipeswhich lead to robust occlusion models inductively satisfying the first two stages ofthe binding mechanism (grouping/segregation). Models leveraging these recipesoutperform existing video action-detectors under occlusion by 32.3% on O-UCF,32.7% on O-JHMDB & 2.6% on Real-OUCF in terms of the vMAP metric. The code for this work has been released at https: //github.com/rajatmodi62/OccludedActionBenchmark.

A critical object detection task is finetuning an existing model to detect novel objects, but the standard workflow requires bounding box annotations which are time-consuming and expensive to collect. Weakly supervised object detection (WSOD) offers an appealing alternative, where object detectors can be trained using image-level labels. However, the practical application of current WSOD models is limited, as they only operate at small data scales and require multiple rounds of training and refinement. To address this, we propose the Weakly Supervised Detection Transformer, which enables efficient knowledge transfer from a large-scale pretraining dataset to WSOD finetuning on hundreds of novel objects. Additionally, we leverage pretrained knowledge to improve the multiple instance learning (MIL) framework often used in WSOD methods. Our experiments show that our approach outperforms previous state-of-the-art models on large-scale novel object detection datasets, and our scaling study reveals that class quantity is more important than image quantity for WSOD pretraining.

Benno Krojer, Vaibhav Adlakha, Vibhav Vineet, Yash Goyal, Edoardo Ponti, Siva Reddy. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2022.

Contrastive learning relies on an assumption that positive pairs contain related views that share certain underlying information about an instance, e.g., patches of an image or co-occurring multimodal signals of a video. What if this assumption is violated? The literature suggests that contrastive learning produces suboptimal representations in the presence of noisy views, e.g., false positive pairs with no apparent shared information. In this work, we pro-pose a new contrastive loss function that is robust against noisy views. We provide rigorous theoretical justifications by showing connections to robust symmetric losses for noisy binary classification and by establishing a new contrastive bound for mutual information maximization based on the Wasserstein distance measure. The proposed loss is completely modality-agnostic and a simple drop-in replacement for the InfoNCE loss, which makes it easy to apply to ex-isting contrastive frameworks. We show that our approach provides consistent improvements over the state-of-the-art on image, video, and graph contrastive learning bench-marks that exhibit a variety of real-world noise patterns.

State-of-the-art methods for self-supervised sequential action alignment rely on deep networks that find correspondences across videos in time. They either learn frame-to-frame mapping across sequences, which does not leverage temporal information, or assume monotonic alignment between each video pair, which ignores variations in the order of actions. As such, these methods are not able to deal with common real-world scenarios that involve background frames or videos that contain non-monotonic sequence of actions. In this paper, we propose an approach to align sequential actions in the wild that involve diverse temporal variations. To this end, we propose an approach to enforce temporal priors on the optimal transport matrix, which leverages temporal consistency, while allowing for variations in the order of actions. Our model accounts for both monotonic and non-monotonic sequences and handles background frames that should not be aligned. We demonstrate that our approach consistently outperforms the state-of-the-art in self-supervised sequential action representation learning on four different benchmark datasets. Code is publicly available at https://github.com/weizheliu/VAVA.

Simulating realistic sensors is a challenging part in data generation for autonomous systems, often involving carefully handcrafted sensor design, scene properties, and physics modeling. To alleviate this, we introduce a pipeline for data-driven simulation of a realistic LiDAR sensor. We propose a model that learns a mapping between RGB images and corresponding LiDAR features such as raydrop or perpoint intensities directly from real datasets. We show that our model can learn to encode realistic effects such as dropped points on transparent surfaces or high intensity returns on reflective materials. When applied to naively raycasted point clouds provided by off-the-shelf simulator software, our model enhances the data by predicting intensities and removing points based on the scene's appearance to match a real LiDAR sensor. We use our technique to learn models of two distinct LiDAR sensors and use them to improve simulated LiDAR data accordingly. Through a sample task of vehicle segmentation, we show that enhancing simulated point clouds with our technique improves downstream task performance.

Being able to reproduce physical phenomena ranging from light interaction to contact mechanics, simulators are becoming increasingly useful in more and more application domains where real-world interaction or labeled data are difficult to obtain. Despite recent progress, significant human effort is needed to configure simulators to accurately reproduce real-world behavior. We introduce a pipeline that combines inverse rendering with differentiable simulation to create digital twins of real-world articulated mechanisms from depth or RGB videos. Our approach automatically discovers joint types and estimates their kinematic parameters, while the dynamic properties of the overall mechanism are tuned to attain physically accurate simulations. Control policies optimized in our derived simulation transfer successfully back to the original system, as we demonstrate on a simulated system. Further, our approach accurately reconstructs the kinematic tree of an articulated mechanism being manipulated by a robot, and highly nonlinear dynamics of a real-world coupled pendulum mechanism. Website: https://eric-heiden.github.io/video2sim

We introduce 3DB: an extendable, unified framework for testing and debugging vision models using photorealistic simulation. We demonstrate, through a wide range of use cases, that 3DB allows users to discover vulnerabilities in computer vision systems and gain insights into how models make decisions. 3DB captures and generalizes many robustness analyses from prior work, and enables one to study their interplay. Finally, we find that the insights generated by the system transfer to the physical world. 3DB will be released as a library alongside a set of examples and documentation. We attach 3DB to the submission.

Joint visual and language modeling on large-scale datasets has recently shown good progress in multi-modal tasks when compared to single modal learning. However, robustness of these approaches against real-world perturbations has not been studied. In this work, we perform the first extensive robustness study of video-language models against various real-world perturbations. We focus on text-to-video retrieval and propose two large-scale benchmark datasets, MSRVTT-P and YouCook2-P, which utilize 90 different visual and 35 different text perturbations. The study reveals some interesting initial findings from the studied models: 1) models are more robust when text is perturbed versus when video is perturbed, 2) models that are pre-trained are more robust than those trained from scratch, 3) models attend more to scene and objects rather than motion and action. We hope this study will serve as a benchmark and guide future research in robust video-language learning. The benchmark introduced in this study along with the code and datasets is available at https://bit.ly/3CNOly4.

Acoustic scattering is strongly influenced by boundary geometry of objects over which sound scatters. The present work proposes a method to infer object geometry from scattering features by training convolutional neural networks. The training data is generated from a fast numerical solver developed on CUDA. The complete set of simulations is sampled to generate multiple datasets containing different amounts of channels and diverse image resolutions. The robustness of our approach in response to data degradation is evaluated by comparing the performance of networks trained using the datasets with varying levels of data degradation. The present work has found that the predictions made from our models match ground truth with high accuracy. In addition, accuracy does not degrade when fewer data channels or lower resolutions are used.

Recent work has shown that the structure of convolutional neural networks (CNNs) induces a strong prior that favors natural images. This prior, known as a deep image prior (DIP), is an effective regularizer in inverse problems such as image denoising and inpainting. We extend the concept of the DIP to depth images. Given color images and noisy and incomplete target depth maps, we optimize a randomly-initialized CNN model to reconstruct a depth map restored by virtue of using the CNN network structure as a prior combined with a view-constrained photo-consistency loss. This loss is computed using images from a geometrically calibrated camera from nearby viewpoints. We apply this deep depth prior for inpainting and refining incomplete and noisy depth maps within both binocular and multi-view stereo pipelines. Our quantitative and qualitative evaluation shows that our refined depth maps are more accurate and complete, and after fusion, produces dense 3D models of higher quality.

Although 3D Convolutional Neural Networks (CNNs) are essential for most learning based applications involving dense 3D data, their applicability is limited due to excessive memory and computational requirements. Compressing such networks by pruning therefore becomes highly desirable. However, pruning 3D CNNs is largely unexplored possibly because of the complex nature of typical pruning algorithms that embeds pruning into an iterative optimization paradigm. In this work, we introduce a Resource Aware Neuron Pruning (RANP) algorithm that prunes 3D CNNs at initialization to high sparsity levels. Specifically, the core idea is to obtain an importance score for each neuron based on their sensitivity to the loss function. This neuron importance is then reweighted according to the neuron resource consumption related to FLOPs or memory. We demonstrate the effectiveness of our pruning method on 3D semantic segmentation with widely used 3D-UNets on ShapeNet and BraTS'18 as well as on video classification with MobileNetV2 and I3D on UCF101 dataset. In these experiments, our RANP leads to roughly 50%-95% reduction in FLOPs and 35%-80% reduction in memory with negligible loss in accuracy compared to the unpruned networks. This significantly reduces the computational resources required to train 3D CNNs. The pruned network obtained by our algorithm can also be easily scaled up and transferred to another dataset for training.

Diffracted scattering and occlusion are important acoustic effects in interactive auralization and noise control applications, typically requiring expensive numerical simulation. We propose training a convolutional neural network to map from a convex scatterer's cross-section to a 2D slice of the resulting spatial loudness distribution. We show that employing a full-resolution residual network for the resulting image-to-image regression problem yields spatially detailed loudness fields with a root-mean-squared error of less than 1 dB, at over 100x speedup compared to full wave simulation.

Machines are a long way from robustly solving open-world perception-control tasks, such as first-person view (FPV) aerial navigation. While recent advances in end-to- end Machine Learning, especially Imitation Learning and Reinforcement appear promising, they are constrained by the need of large amounts of difficult-to-collect labeled real- world data. Simulated data, on the other hand, is easy to generate, but generally does not render safe behaviors in diverse real-life scenarios. In this work we propose a novel method for learning robust visuomotor policies for real-world deployment which can be trained purely with simulated data. We develop rich state representations that combine supervised and unsupervised environment data. Our approach takes a cross-modal perspective, where separate modalities correspond to the raw camera data and the system states relevant to the task, such as the relative pose of gates to the drone in the case of drone racing. We feed both data modalities into a novel factored architecture, which learns a joint lowdimensional embedding via Variational Auto Encoders. This compact representation is then fed into a control policy, which we trained using imitation learning with expert trajectories in a simulator. We analyze the rich latent spaces learned with our proposed representations, and show that the use of our cross-modal architecture significantly improves control policy performance as compared to end-to-end learning or purely unsupervised feature extractors. We also present real-world results for drone navigation through gates in different track configurations and environmental conditions. Our proposed method, which runs fully onboard, can successfully generalize the learned representations and policies across simulation and reality, significantly outperforming baseline approaches.

We present an approach to synthesize highly photorealistic images of 3D object models, which we use to train a convolutional neural network for detecting the objects in real images. The proposed approach has three key ingredients: (1) 3D object models are rendered in 3D models of complete scenes with realistic materials and lighting, (2) plausible geometric configuration of objects and cameras in a scene is generated using physics simulation, and (3) high photorealism of the synthesized images is achieved by physically based rendering. When trained on images synthesized by the proposed approach, the Faster R-CNN object detector [1] achieves a 24% absolute improvement of [email protected] on Rutgers APC [2] and 11% on LineMod-Occluded [3] datasets, compared to a baseline where the training images are synthesized by rendering object models on top of random photographs. This work is a step towards being able to effectively train object detectors without capturing or annotating any real images. A dataset of 400K synthetic images with ground truth annotations for various computer vision tasks will be released on the project website: thodan.github.io/objectsynth.

We present an approach to long-range spatio-temporal regularization in semantic video segmentation. Temporal regularization in video is challenging because both the camera and the scene may be in motion. Thus Euclidean distance in the space-time volume is not a good proxy for correspondence. We optimize the mapping of pixels to a Euclidean feature space so as to minimize distances between corresponding points. Structured prediction is performed by a dense CRF that operates on the optimized features. Experimental results demonstrate that the presented approach increases the accuracy and temporal consistency of semantic video segmentation.

We present an approach to dense depth estimation from a single monocular camera that is moving through a dynamic scene. The approach produces a dense depth map from two consecutive frames. Moving objects are reconstructed along with the surrounding environment. We provide a novel motion segmentation algorithm that segments the optical flow field into a set of motion models, each with its own epipolar geometry. We then show that the scene can be reconstructed based on these motion models by optimizing a convex program. The optimization jointly reasons about the scales of different objects and assembles the scene in a common coordinate frame, determined up to a global scale. Experimental results demonstrate that the presented approach outperforms prior methods for monocular depth estimation in dynamic scenes.

Adaptive tracking-by-detection methods are widely used in computer vision for tracking arbitrary objects. Current approaches treat the tracking problem as a classification task and use online learning techniques to update the object model. However, for these updates to happen one needs to convert the estimated object position into a set of labelled training examples, and it is not clear how best to perform this intermediate step. Furthermore, the objective for the classifier (label prediction) is not explicitly coupled to the objective for the tracker (estimation of object position). In this paper, we present a framework for adaptive visual object tracking based on structured output prediction. By explicitly allowing the output space to express the needs of the tracker, we avoid the need for an intermediate classification step. Our method uses a kernelised structured output support vector machine (SVM), which is learned online to provide adaptive tracking. To allow our tracker to run at high frame rates, we (a) introduce a budgeting mechanism that prevents the unbounded growth in the number of support vectors that would otherwise occur during tracking, and (b) show how to implement tracking on the GPU. Experimentally, we show that our algorithm is able to outperform state-of-the-art trackers on various benchmark videos. Additionally, we show that we can easily incorporate additional features and kernels into our framework, which results in increased tracking performance.

We present an augmented reality system for large scale 3D reconstruction and recognition in outdoor scenes. Unlike existing prior work, which tries to reconstruct scenes using active depth cameras, we use a purely passive stereo setup, allowing for outdoor use and extended sensing range. Our system not only produces a map of the 3D environment in real-time, it also allows the user to draw (or 'paint') with a laser pointer directly onto the reconstruction to segment the model into objects. Given these examples our system then learns to segment other parts of the 3D map during online acquisition. Unlike typical object recognition systems, ours therefore very much places the user 'in the loop' to segment particular objects of interest, rather than learning from predefined databases. The laser pointer additionally helps to 'clean up' the stereo reconstruction and final 3D map, interactively. Using our system, within minutes, a user can capture a full 3D map, segment it into objects of interest, and refine parts of the model during capture. We provide full technical details of our system to aid replication, as well as quantitative evaluation of system components. We demonstrate the possibility of using our system for helping the visually impaired navigate through spaces. Beyond this use, our system can be used for playing large-scale augmented reality games, shared online to augment streetview data, and used for more detailed car and person navigation.

Pixel-level labelling tasks, such as semantic segmentation, play a central role in image understanding. Recent approaches have attempted to harness the capabilities of deep learning techniques for image recognition to tackle pixel-level labelling tasks. One central issue in this methodology is the limited capacity of deep learning techniques to delineate visual objects. To solve this problem, we introduce a new form of convolutional neural network that combines the strengths of Convolutional Neural Networks (CNNs) and Conditional Random Fields (CRFs)-based probabilistic graphical modelling. To this end, we formulate Conditional Random Fields with Gaussian pairwise potentials and mean-field approximate inference as Recurrent Neural Networks. This network, called CRF-RNN, is then plugged in as a part of a CNN to obtain a deep network that has desirable properties of both CNNs and CRFs. Importantly, our system fully integrates CRF modelling with CNNs, making it possible to train the whole deep network end-to-end with the usual back-propagation algorithm, avoiding offline post-processing methods for object delineation. We apply the proposed method to the problem of semantic image segmentation, obtaining top results on the challenging Pascal VOC 2012 segmentation benchmark.

Our abilities in scene understanding, which allow us to perceive the 3D structure of our surroundings and intuitively recognise the objects we see, are things that we largely take for granted, but for robots, the task of understanding large scenes quickly remains extremely challenging. Recently, scene understanding approaches based on 3D reconstruction and semantic segmentation have become popular, but existing methods either do not scale, fail outdoors, provide only sparse reconstructions or are rather slow. In this paper, we build on a recent hash-based technique for large-scale fusion and an efficient mean-field inference algorithm for densely-connected CRFs to present what to our knowledge is the first system that can perform dense, large-scale, outdoor semantic reconstruction of a scene in (near) real time. We also present a `semantic fusion' approach that allows us to handle dynamic objects more effectively than previous approaches. We demonstrate the effectiveness of our approach on the KITTI dataset, and provide qualitative and quantitative results showing high-quality dense reconstruction and labelling of a number of scenes.

Aquiring reliable depth maps is an essential prerequisite for accurate and incremental 3D reconstruction used in a variety of robotics applications. Depth maps produced by affordable Kinect-like cameras have become a de-facto standard for indoor reconstruction and the driving force behind the success of many algorithms. However, Kinect-like cameras are less effective outdoors where one should rely on other sensors. Often, we use a combination of a stereo camera and lidar, however, process the acquired data in independent pipelines which generally leads to sub-optimal performance since both sensors suffer from different drawbacks. In this paper, we propose a probabilistic model that efficiently exploits complementarity between different depth-sensing modalities for incremental dense scene reconstruction. Our model uses a piecewise planarity prior assumption which is common in both the indoor and outdoor scenes. We demonstrate the effectiveness of our approach on the KITTI dataset, and provide qualitative and quantitative results showing high-quality dense reconstruction of a number of scenes.

We present a new interactive and online approach to 3D scene understanding. Our system, SemanticPaint , allows users to simultaneously scan their environment whilst interactively segmenting the scene simply by reaching out and touching any desired object or surface. Our system continuously learns from these segmentations, and labels new unseen parts of the environment. Unlike offline systems where capture, labeling, and batch learning often take hours or even days to perform, our approach is fully online. This provides users with continuous live feedback of the recognition during capture, allowing to immediately correct errors in the segmentation and/or learning—a feature that has so far been unavailable to batch and offline methods. This leads to models that are tailored or personalized specifically to the user's environments and object classes of interest, opening up the potential for new applications in augmented reality, interior design, and human/robot navigation. It also provides the ability to capture substantial labeled 3D datasets for training large-scale visual recognition systems.

The concepts of objects and attributes are both important for describing images precisely, since verbal descriptions often contain both adjectives and nouns (e.g. 'I see a shiny red chair'). In this paper, we formulate the problem of joint visual attribute and object class image segmentation as a dense multi-labelling problem, where each pixel in an image can be associated with both an object-class and a set of visual attributes labels. In order to learn the label correlations, we adopt a boosting-based piecewise training approach with respect to the visual appearance and co-occurrence cues. We use a filtering-based mean-field approximation approach for efficient joint inference. Further, we develop a hierarchical model to incorporate region-level object and attribute information. Experiments on the aPASCAL, CORE and attribute augmented NYU indoor scenes datasets show that the proposed approach is able to achieve state-of-the-art results.

Humans describe images in terms of nouns and adjectives while algorithms operate on images represented as sets of pixels. Bridging this gap between how humans would like to access images versus their typical representation is the goal of image parsing, which involves assigning object and attribute labels to pixels. In this article we propose treating nouns as object labels and adjectives as visual attribute labels. This allows us to formulate the image parsing problem as one of jointly estimating per-pixel object and attribute labels from a set of training images. We propose an efficient (interactive time) solution. Using the extracted labels as handles, our system empowers a user to verbally refine the results. This enables hands-free parsing of an image into pixel-wise object/attribute labels that correspond to human semantics. Verbally selecting objects of interest enables a novel and natural interaction modality that can possibly be used to interact with new generation devices (e.g., smartphones, Google Glass, livingroom devices). We demonstrate our system on a large number of real-world images with varying complexity. To help understand the trade-offs compared to traditional mouse-based interactions, results are reported for both a large-scale quantitative evaluation and a user study.

Detecting visually salient regions in images is one of the fundamental problems in computer vision. We propose a novel method to decompose an image into large scale perceptually homogeneous elements for efficient salient region detection, using a soft image abstraction representation. By considering both appearance similarity and spatial distribution of image pixels, the proposed representation abstracts out unnecessary image details, allowing the assignment of comparable saliency values across similar regions, and producing perceptually accurate salient region detection. We evaluate our salient region detection approach on the largest publicly available dataset with pixel accurate annotations. The experimental results show that the proposed method outperforms 18 alternate methods, reducing the mean absolute error by 25.2% compared to the previous best result, while being computationally more efficient.

Many methods have been proposed to recover the intrinsic scene properties such as shape, reflectance and illumination from a single image. However, most of these models have been applied on laboratory datasets. In this work we explore the synergy effects between intrinsic scene properties recovered from an image, and the objects and attributes present in the scene. We cast the problem in a joint energy minimization framework; thus our model is able to encode the strong correlations between intrinsic properties (reflectance, shape, illumination), objects (table, tv-monitor), and materials (wooden, plastic) in a given scene. We tested our approach on the NYU and Pascal datasets, and observe both qualitative and quantitative improvements in the overall accuracy.

Recently, Krahenbuhl and Koltun proposed an efficient inference method for densely connected pairwise random fields using the mean-field approximation for a Conditional Random Field (CRF). However, they restrict their pairwise weights to take the form of a weighted combination of Gaussian kernels where each Gaussian component is allowed to take only zero mean, and can only be rescaled by a single value for each label pair. Further, their method is sensitive to initialization. In this paper, we propose methods to alleviate these issues. First, we propose a hierarchical mean-field approach where labelling from the coarser level is propagated to the finer level for better initialisation. Further, we use SIFT-flow based label transfer to provide a good initial condition at the coarsest level. Second, we allow our approach to take general Gaussian pairwise weights, where we learn the mean, the co-variance matrix, and the mixing co-efficient for every mixture component. We propose a variation of Expectation Maximization (EM) for piecewise learning of the parameters of the mixture model determined by the maximum likelihood function. Finally, we demonstrate the efficiency and accuracy offered by our method for object class segmentation problems on two challenging datasets: PascalVOC-10 segmentation and CamVid datasets. We show that we are able to achieve state of the art performance on the CamVid dataset, and an almost 3% improvement on the PascalVOC10 dataset compared to baseline graph-cut and mean-field methods, while also reducing the inference time by almost a factor of 3 compared to graph-cuts based methods.

A large number of problems in computer vision can be modeled as energy minimization problems in a markov random field (MRF) framework. Many methods have been developed over the years for efficient inference, especially in pairwise MRFs. In general there is a trade-off between the complexity/efficiency of the algorithm and its convergence properties, with certain problems requiring more complex inference to handle general pairwise potentials. Graphcuts based α-expansion performs well on certain classes of energies, and sequential tree reweighted message passing (TRWS) and loopy belief propagation (LBP) can be used for non-submodular cases. These methods though suffer from poor convergence and often oscillate between solutions. In this paper, we propose a tiered move making algorithm which is an iterative method. Each move to the next configuration is based on the current labeling and an optimal tiered move, where each tiered move requires one application of the dynamic programming based tiered labeling method introduced in Felzenszwalb et. al. [2]. The algorithm converges to a local minimum for any general pairwise potential, and we give a theoretical analysis of the properties of the algorithm, characterizing the situations in which we can expect good performance. We evaluate the algorithm on many benchmark labeling problems such as stereo, image segmentation, image stitching and image denoising, as well as random energy minimization. Our method consistently gets better energy values than α-expansion, LBP, quadratic pseudo-boolean optimization (QPBO), and is competitive with TRWS.

In this work, we propose a method for instance based human segmentation in images and videos, extending the recent detector-based conditional random field model of Ladicky et.al. Instance based human segmentation involves pixel level labeling of an image, partitioning it into distinct human instances and background. To achieve our goal, we add three new components to their framework. First, we include human partsbased detection potentials to take advantage of the structure present in human instances. Further, in order to generate a consistent segmentation from different human parts, we incorporate shape prior information, which biases the segmentation to characteristic overall human shapes. Also, we enhance the representative power of the energy function by adopting exemplar instance based matching terms, which helps our method to adapt easily to different human sizes and poses. Finally, we extensively evaluate our proposed method on the Buffy dataset with our new segmented ground truth images, and show a substantial improvement over existing CRF methods. These new annotations will be made available for future use as well.