Facial expression spotting is a significant but challenging task in facial expression analysis. The accuracy of expression spotting is affected not only by irrelevant facial movements but also by the difficulty of perceiving subtle motions in micro-expressions. In this paper, we propose a Multi-Scale Spatio-Temporal Graph Convolutional Network (SpoT-GCN) for facial expression spotting. To extract more robust motion features, we track both short- and long-term motion of facial muscles in compact sliding windows whose window length adapts to the temporal receptive field of the network. This strategy, termed the receptive field adaptive sliding window strategy, effectively magnifies the motion features while alleviating the problem of severe head movement. The subtle motion features are then converted to a facial graph representation, whose spatio-temporal graph patterns are learned by a graph convolutional network. This network learns both local and global features from multiple scales of facial graph structures using our proposed facial local graph pooling (FLGP). Furthermore, we introduce supervised contrastive learning to enhance the discriminative capability of our model for difficult-to-classify frames. The experimental results on the SAMM-LV and CAS(ME)^2 datasets demonstrate that our method achieves state-of-the-art performance, particularly in micro-expression spotting. Ablation studies further verify the effectiveness of our proposed modules.
We propose a computational imaging method for time-efficient light-field acquisition that combines a coded aperture with an event-based camera. Different from the conventional coded-aperture imaging method, our method applies a sequence of coding patterns during a single exposure for an image frame. The parallax information, which is related to the differences in coding patterns, is recorded as events. The image frame and events, all of which are measured in a single exposure, are jointly used to computationally reconstruct a light field. We also designed an algorithm pipeline for our method that is end-to-end trainable on the basis of deep optics and compatible with real camera hardware. We experimentally showed that our method can achieve more accurate reconstruction than several other imaging methods with a single exposure. We also developed a hardware prototype with the potential to complete the measurement on the camera within 22 msec and demonstrated that light fields from real 3-D scenes can be obtained with convincing visual quality. Our software and supplementary video are available from our project website.
Multi-view inverse rendering is the problem of estimating the scene parameters such as shapes, materials, or illuminations from a sequence of images captured under different viewpoints. Many approaches, however, assume single light bounce and thus fail to recover challenging scenarios like inter-reflections. On the other hand, simply extending those methods to consider multi-bounced light requires more assumptions to alleviate the ambiguity. To address this problem, we propose Neural Incident Stokes Fields (NeISF), a multi-view inverse rendering framework that reduces ambiguities using polarization cues. The primary motivation for using polarization cues is that it is the accumulation of multi-bounced light, providing rich information about geometry and material. Based on this knowledge, the proposed incident Stokes field efficiently models the accumulated polarization effect with the aid of an original physically-based differentiable polarimetric renderer. Lastly, experimental results show that our method outperforms the existing works in synthetic and real scenarios.
Large-scale models trained on extensive datasets, have emerged as the preferred approach due to their high generalizability across various tasks. In-context learning (ICL), a popular strategy in natural language processing, uses such models for different tasks by providing instructive prompts but without updating model parameters. This idea is now being explored in computer vision, where an input-output image pair (called an in-context pair) is supplied to the model with a query image as a prompt to exemplify the desired output. The efficacy of visual ICL often depends on the quality of the prompts. We thus introduce a method coined Instruct Me More (InMeMo), which augments in-context pairs with a learnable perturbation (prompt), to explore its potential. Our experiments on mainstream tasks reveal that InMeMo surpasses the current state-of-the-art performance. Specifically, compared to the baseline without learnable prompt, InMeMo boosts mIoU scores by 7.35 and 15.13 for foreground segmentation and single object detection tasks, respectively. Our findings suggest that InMeMo offers a versatile and efficient way to enhance the performance of visual ICL with lightweight training. Code is available at https://github.com/Jackieam/InMeMo.
In this work, we propose an inverse rendering model that estimates 3D shape, spatially-varying reflectance, homogeneous subsurface scattering parameters, and an environment illumination jointly from only a pair of captured images of a translucent object. In order to solve the ambiguity problem of inverse rendering, we use a physically-based renderer and a neural renderer for scene reconstruction and material editing. Because two renderers are differentiable, we can compute a reconstruction loss to assist parameter estimation. To enhance the supervision of the proposed neural renderer, we also propose an augmented loss. In addition, we use a flash and no-flash image pair as the input. To supervise the training, we constructed a large-scale synthetic dataset of translucent objects, which consists of 117K scenes. Qualitative and quantitative results on both synthetic and real-world datasets demonstrated the effectiveness of the proposed model.
Interpreting and explaining the behavior of deep neural networks is critical for many tasks. Explainable AI provides a way to address this challenge, mostly by providing per-pixel relevance to the decision. Yet, interpreting such explanations may require expert knowledge. Some recent attempts toward interpretability adopt a concept-based framework, giving a higher-level relationship between some concepts and model decisions. This paper proposes Bottleneck Concept Learner (BotCL), which represents an image solely by the presence/absence of concepts learned through training over the target task without explicit supervision over the concepts. It uses self-supervision and tailored regularizers so that learned concepts can be human-understandable. Using some image classification tasks as our testbed, we demonstrate BotCL's potential to rebuild neural networks for better interpretability. Code is available at https://github.com/wbw520/BotCL and a simple demo is available at https://botcl.liangzhili.com/.
Lensless imaging protects visual privacy by capturing heavily blurred images that are imperceptible for humans to recognize the subject but contain enough information for machines to infer information. Unfortunately, protecting visual privacy comes with a reduction in recognition accuracy and vice versa. We propose a learnable lensless imaging framework that protects visual privacy while maintaining recognition accuracy. To make captured images imperceptible to humans, we designed several loss functions based on total variation, invertibility, and the restricted isometry property. We studied the effect of privacy protection with blurriness on the identification of personal identity via a quantitative method based on a subjective evaluation. Moreover, we validate our simulation by implementing a hardware realization of lensless imaging with photo-lithographically printed masks.
Vision Transformers (ViTs) are becoming a very popular paradigm for vision tasks as they achieve state-of-the-art performance on image classification. However, although early works implied that this network structure had increased robustness against adversarial attacks, some works argue ViTs are still vulnerable. This paper presents our first attempt toward detecting adversarial attacks during inference time using the network's input and outputs as well as latent features. We design four quantifications (or derivatives) of input, output, and latent vectors of ViT-based models that provide a signature of the inference, which could be beneficial for the attack detection, and empirically study their behavior over clean samples and adversarial samples. The results demonstrate that the quantifications from input (images) and output (posterior probabilities) are promising for distinguishing clean and adversarial samples, while latent vectors offer less discriminative power, though they give some insights on how adversarial perturbations work.
Video summarization aims to select the most informative subset of frames in a video to facilitate efficient video browsing. Unsupervised methods usually rely on heuristic training objectives such as diversity and representativeness. However, such methods need to bootstrap the online-generated summaries to compute the objectives for importance score regression. We consider such a pipeline inefficient and seek to directly quantify the frame-level importance with the help of contrastive losses in the representation learning literature. Leveraging the contrastive losses, we propose three metrics featuring a desirable key frame: local dissimilarity, global consistency, and uniqueness. With features pre-trained on the image classification task, the metrics can already yield high-quality importance scores, demonstrating competitive or better performance than past heavily-trained methods. We show that by refining the pre-trained features with a lightweight contrastively learned projection module, the frame-level importance scores can be further improved, and the model can also leverage a large number of random videos and generalize to test videos with decent performance. Code available at https://github.com/pangzss/pytorch-CTVSUM.
We tackle the problem of modeling light scattering in homogeneous translucent material and estimating its scattering parameters. A scattering phase function is one of such parameters which affects the distribution of scattered radiation. It is the most complex and challenging parameter to be modeled in practice, and empirical phase functions are usually used. Empirical phase functions (such as Henyey-Greenstein (HG) phase function or its modified ones) are usually presented and limited to a specific range of scattering materials. This limitation raises concern for an inverse rendering problem where the target material is generally unknown. In such a situation, a more general phase function is preferred. Although there exists such a general phase function in the polynomial form using a basis such as Legendre polynomials \cite{Fowler1983}, inverse rendering with this phase function is not straightforward. This is because the base polynomials may be negative somewhere, while a phase function cannot. This research presents a novel general phase function that can avoid this issue and an inverse rendering application using this phase function. The proposed phase function was positively evaluated with a wide range of materials modeled with Mie scattering theory. The scattering parameters estimation with the proposed phase function was evaluated with simulation and real-world experiments.