David J. Crandall

Vibhas K. Vats, Sripad Joshi, David J. Crandall et al.

Traditional multi-view stereo (MVS) methods rely heavily on photometric and geometric consistency constraints, but newer machine learning-based MVS methods check geometric consistency across multiple source views only as a post-processing step. In this paper, we present a novel approach that explicitly encourages geometric consistency of reference view depth maps across multiple source views at different scales during learning (see Fig. 1). We find that adding this geometric consistency loss significantly accelerates learning by explicitly penalizing geometrically inconsistent pixels, reducing the training iteration requirements to nearly half that of other MVS methods. Our extensive experiments show that our approach achieves a new state-of-the-art on the DTU and BlendedMVS datasets, and competitive results on the Tanks and Temples benchmark. To the best of our knowledge, GC-MVSNet is the first attempt to enforce multi-view, multi-scale geometric consistency during learning.

Vibhas Kumar Vats, David J. Crandall, Samuel Goree

AI training datasets will inevitably contain AI-generated examples, leading to ``feedback'' in which the output of one model impacts the training of another. It is known that such iterative feedback can lead to model collapse, yet the mechanisms underlying this degeneration remain poorly understood. Here we show that a broad class of feedback processes converges to a low-dimensional invariant structure in latent space, a phenomenon we call neural resonance. By modeling iterative feedback as a Markov Chain, we show that two conditions are needed for this resonance to occur: ergodicity of the feedback process and directional contraction of the latent representation. By studying diffusion models on MNIST and ImageNet, as well as CycleGAN and an audio feedback experiment, we map how local and global manifold geometry evolve, and we introduce an eight-pattern taxonomy of collapse behaviors. Neural resonance provides a unified explanation for long-term degenerate behavior in generative models and provides practical diagnostics for identifying, characterizing, and eventually mitigating collapse.

Chuhua Wang, Yuchen Wang, Mingze Xu et al.

We propose to predict the future trajectories of observed agents (e.g., pedestrians or vehicles) by estimating and using their goals at multiple time scales. We argue that the goal of a moving agent may change over time, and modeling goals continuously provides more accurate and detailed information for future trajectory estimation. To this end, we present a recurrent network for trajectory prediction, called Stepwise Goal-Driven Network (SGNet). Unlike prior work that models only a single, long-term goal, SGNet estimates and uses goals at multiple temporal scales. In particular, it incorporates an encoder that captures historical information, a stepwise goal estimator that predicts successive goals into the future, and a decoder that predicts future trajectory. We evaluate our model on three first-person traffic datasets (HEV-I, JAAD, and PIE) as well as on three bird's eye view datasets (NuScenes, ETH, and UCY), and show that our model achieves state-of-the-art results on all datasets. Code has been made available at: https://github.com/ChuhuaW/SGNet.pytorch.

Yu Wang, Juhyung Ha, Frangil M. Ramirez et al.

Active Speaker Detection (ASD) aims to identify who is currently speaking in each frame of a video. Most state-of-the-art approaches rely on late fusion to combine visual and audio features, but late fusion often fails to capture fine-grained cross-modal interactions, which can be critical for robust performance in unconstrained scenarios. In this paper, we introduce GateFusion, a novel architecture that combines strong pretrained unimodal encoders with a Hierarchical Gated Fusion Decoder (HiGate). HiGate enables progressive, multi-depth fusion by adaptively injecting contextual features from one modality into the other at multiple layers of the Transformer backbone, guided by learnable, bimodally-conditioned gates. To further strengthen multimodal learning, we propose two auxiliary objectives: Masked Alignment Loss (MAL) to align unimodal outputs with multimodal predictions, and Over-Positive Penalty (OPP) to suppress spurious video-only activations. GateFusion establishes new state-of-the-art results on several challenging ASD benchmarks, achieving 77.8% mAP (+9.4%), 86.1% mAP (+2.9%), and 96.1% mAP (+0.5%) on Ego4D-ASD, UniTalk, and WASD benchmarks, respectively, and delivering competitive performance on AVA-ActiveSpeaker. Out-of-domain experiments demonstrate the generalization of our model, while comprehensive ablations show the complementary benefits of each component.

Haoran Liu, Anthony Tai, David J. Crandall et al.

Neural tangent kernels (NTKs) have been proposed to study the behavior of trained neural networks from the perspective of Gaussian processes. An important result in this body of work is the theorem of equivalence between a trained neural network and kernel regression with the corresponding NTK. This theorem allows for an interpretation of neural networks as special cases of kernel regression. However, does this theorem of equivalence hold in practice? In this paper, we revisit the derivation of the NTK rigorously and conduct numerical experiments to evaluate this equivalence theorem. We observe that adding a layer to a neural network and the corresponding updated NTK do not yield matching changes in the predictor error. Furthermore, we observe that kernel regression with a Gaussian process kernel in the literature that does not account for neural network training produces prediction errors very close to that of kernel regression with NTKs. These observations suggest the equivalence theorem does not hold well in practice and puts into question whether neural tangent kernels adequately address the training process of neural networks.

Frangil Ramirez, Elizabeth Clerkin, David J. Crandall et al.

Young children readily recognize and generalize visual objects labeled by common nouns, suggesting that these basic level object categories may be given. Yet if they are, how they arise remains unclear. We propose that the answer lies in the statistics of infant daily life visual experiences. Whereas large and diverse datasets typically support robust learning and generalization in human and machine learning, infants achieve this generalization from limited experiences. We suggest that the resolution of this apparent contradiction lies in the visual diversity of daily life, repeated experiences with single object instances. Analyzing egocentric images from 14 infants (aged 7 to 11 months) we show that their everyday visual input exhibits a lumpy similarity structure, with clusters of highly similar images interspersed with rarer, more variable ones, across eight early-learned categories. Computational experiments show that mimicking this structure in machines improves generalization from small datasets in machine learning. The natural lumpiness of infant experience may thus support early category learning and generalization and, more broadly, offer principles for efficient learning across a variety of problems and kinds of learners.

Yu Wang, Juhyung Ha, David J. Crandall

Active speaker detection (ASD) in egocentric videos presents unique challenges due to unstable viewpoints, motion blur, and off-screen speech sources - conditions under which traditional visual-centric methods degrade significantly. We introduce PAIR-Net (Pretrained Audio-Visual Integration with Regularization Network), an effective model that integrates a partially frozen Whisper audio encoder with a fine-tuned AV-HuBERT visual backbone to robustly fuse cross-modal cues. To counteract modality imbalance, we introduce an inter-modal alignment loss that synchronizes audio and visual representations, enabling more consistent convergence across modalities. Without relying on multi-speaker context or ideal frontal views, PAIR-Net achieves state-of-the-art performance on the Ego4D ASD benchmark with 76.6% mAP, surpassing LoCoNet and STHG by 8.2% and 12.9% mAP, respectively. Our results highlight the value of pretrained audio priors and alignment-based fusion for robust ASD under real-world egocentric conditions.

Zhenhua Chen, Chuhua Wang, David J. Crandall

Segmentation models have been found to be vulnerable to targeted and non-targeted adversarial attacks. However, the resulting segmentation outputs are often so damaged that it is easy to spot an attack. In this paper, we propose semantically stealthy adversarial attacks which can manipulate targeted labels while preserving non-targeted labels at the same time. One challenge is making semantically meaningful manipulations across datasets and models. Another challenge is avoiding damaging non-targeted labels. To solve these challenges, we consider each input image as prior knowledge to generate perturbations. We also design a special regularizer to help extract features. To evaluate our model's performance, we design three basic attack types, namely `vanishing into the context,' `embedding fake labels,' and `displacing target objects.' Our experiments show that our stealthy adversarial model can attack segmentation models with a relatively high success rate on Cityscapes, Mapillary, and BDD100K. Our framework shows good empirical generalization across datasets and models.

Mang Ye, Jianbing Shen, David J. Crandall et al.

Visible-infrared person re-identification (VI-ReID) is a challenging cross-modality pedestrian retrieval problem. Due to the large intra-class variations and cross-modality discrepancy with large amount of sample noise, it is difficult to learn discriminative part features. Existing VI-ReID methods instead tend to learn global representations, which have limited discriminability and weak robustness to noisy images. In this paper, we propose a novel dynamic dual-attentive aggregation (DDAG) learning method by mining both intra-modality part-level and cross-modality graph-level contextual cues for VI-ReID. We propose an intra-modality weighted-part attention module to extract discriminative part-aggregated features, by imposing the domain knowledge on the part relationship mining. To enhance robustness against noisy samples, we introduce cross-modality graph structured attention to reinforce the representation with the contextual relations across the two modalities. We also develop a parameter-free dynamic dual aggregation learning strategy to adaptively integrate the two components in a progressive joint training manner. Extensive experiments demonstrate that DDAG outperforms the state-of-the-art methods under various settings.

Yu Yao, Mingze Xu, Yuchen Wang et al.

Recognizing abnormal events such as traffic violations and accidents in natural driving scenes is essential for successful autonomous driving and advanced driver assistance systems. However, most work on video anomaly detection suffers from two crucial drawbacks. First, they assume cameras are fixed and videos have static backgrounds, which is reasonable for surveillance applications but not for vehicle-mounted cameras. Second, they pose the problem as one-class classification, relying on arduously hand-labeled training datasets that limit recognition to anomaly categories that have been explicitly trained. This paper proposes an unsupervised approach for traffic accident detection in first-person (dashboard-mounted camera) videos. Our major novelty is to detect anomalies by predicting the future locations of traffic participants and then monitoring the prediction accuracy and consistency metrics with three different strategies. We evaluate our approach using a new dataset of diverse traffic accidents, AnAn Accident Detection (A3D), as well as another publicly-available dataset. Experimental results show that our approach outperforms the state-of-the-art.

Mingze Xu, Mingfei Gao, Yi-Ting Chen et al.

Most work on temporal action detection is formulated as an offline problem, in which the start and end times of actions are determined after the entire video is fully observed. However, important real-time applications including surveillance and driver assistance systems require identifying actions as soon as each video frame arrives, based only on current and historical observations. In this paper, we propose a novel framework, Temporal Recurrent Network (TRN), to model greater temporal context of a video frame by simultaneously performing online action detection and anticipation of the immediate future. At each moment in time, our approach makes use of both accumulated historical evidence and predicted future information to better recognize the action that is currently occurring, and integrates both of these into a unified end-to-end architecture. We evaluate our approach on two popular online action detection datasets, HDD and TVSeries, as well as another widely used dataset, THUMOS'14. The results show that TRN significantly outperforms the state-of-the-art.

Yu Yao, Mingze Xu, Chiho Choi et al.

Predicting the future location of vehicles is essential for safety-critical applications such as advanced driver assistance systems (ADAS) and autonomous driving. This paper introduces a novel approach to simultaneously predict both the location and scale of target vehicles in the first-person (egocentric) view of an ego-vehicle. We present a multi-stream recurrent neural network (RNN) encoder-decoder model that separately captures both object location and scale and pixel-level observations for future vehicle localization. We show that incorporating dense optical flow improves prediction results significantly since it captures information about motion as well as appearance change. We also find that explicitly modeling future motion of the ego-vehicle improves the prediction accuracy, which could be especially beneficial in intelligent and automated vehicles that have motion planning capability. To evaluate the performance of our approach, we present a new dataset of first-person videos collected from a variety of scenarios at road intersections, which are particularly challenging moments for prediction because vehicle trajectories are diverse and dynamic.

Satoshi Tsutsui, Tommi Kerola, Shunta Saito et al.

Identifying "free-space," or safely driveable regions in the scene ahead, is a fundamental task for autonomous navigation. While this task can be addressed using semantic segmentation, the manual labor involved in creating pixelwise annotations to train the segmentation model is very costly. Although weakly supervised segmentation addresses this issue, most methods are not designed for free-space. In this paper, we observe that homogeneous texture and location are two key characteristics of free-space, and develop a novel, practical framework for free-space segmentation with minimal human supervision. Our experiments show that our framework performs better than other weakly supervised methods while using less supervision. Our work demonstrates the potential for performing free-space segmentation without tedious and costly manual annotation, which will be important for adapting autonomous driving systems to different types of vehicles and environments

Eman T. Hassan, David J. Crandall

We investigate Generative Adversarial Networks (GANs) to model one particular kind of image: frames from TV cartoons. Cartoons are particularly interesting because their visual appearance emphasizes the important semantic information about a scene while abstracting out the less important details, but each cartoon series has a distinctive artistic style that performs this abstraction in different ways. We consider a dataset consisting of images from two popular television cartoon series, Family Guy and The Simpsons. We examine the ability of GANs to generate images from each of these two domains, when trained independently as well as on both domains jointly. We find that generative models may be capable of finding semantic-level correspondences between these two image domains despite the unsupervised setting, even when the training data does not give labeled alignments between them.

Scott Workman, Menghua Zhai, David J. Crandall et al.

We propose a novel convolutional neural network architecture for estimating geospatial functions such as population density, land cover, or land use. In our approach, we combine overhead and ground-level images in an end-to-end trainable neural network, which uses kernel regression and density estimation to convert features extracted from the ground-level images into a dense feature map. The output of this network is a dense estimate of the geospatial function in the form of a pixel-level labeling of the overhead image. To evaluate our approach, we created a large dataset of overhead and ground-level images from a major urban area with three sets of labels: land use, building function, and building age. We find that our approach is more accurate for all tasks, in some cases dramatically so.

Chenyou Fan, Jangwon Lee, Mingze Xu et al.

We consider scenarios in which we wish to perform joint scene understanding, object tracking, activity recognition, and other tasks in environments in which multiple people are wearing body-worn cameras while a third-person static camera also captures the scene. To do this, we need to establish person-level correspondences across first- and third-person videos, which is challenging because the camera wearer is not visible from his/her own egocentric video, preventing the use of direct feature matching. In this paper, we propose a new semi-Siamese Convolutional Neural Network architecture to address this novel challenge. We formulate the problem as learning a joint embedding space for first- and third-person videos that considers both spatial- and motion-domain cues. A new triplet loss function is designed to minimize the distance between correct first- and third-person matches while maximizing the distance between incorrect ones. This end-to-end approach performs significantly better than several baselines, in part by learning the first- and third-person features optimized for matching jointly with the distance measure itself.

Chenyou Fan, David J. Crandall

Lifelogging cameras capture everyday life from a first-person perspective, but generate so much data that it is hard for users to browse and organize their image collections effectively. In this paper, we propose to use automatic image captioning algorithms to generate textual representations of these collections. We develop and explore novel techniques based on deep learning to generate captions for both individual images and image streams, using temporal consistency constraints to create summaries that are both more compact and less noisy. We evaluate our techniques with quantitative and qualitative results, and apply captioning to an image retrieval application for finding potentially private images. Our results suggest that our automatic captioning algorithms, while imperfect, may work well enough to help users manage lifelogging photo collections.