Shmuel Peleg

Daniel Arkushin, Bar Cohen, Shmuel Peleg et al.

In the Clothes-Changing Re-Identification (CC-ReID) problem, given a query sample of a person, the goal is to determine the correct identity based on a labeled gallery in which the person appears in different clothes. Several models tackle this challenge by extracting clothes-independent features. However, the performance of these models is still lower for the clothes-changing setting compared to the same-clothes setting in which the person appears with the same clothes in the labeled gallery. As clothing-related features are often dominant features in the data, we propose a new process we call Gallery Enrichment, to utilize these features. In this process, we enrich the original gallery by adding to it query samples based on their face features, using an unsupervised algorithm. Additionally, we show that combining ReID and face feature extraction modules alongside an enriched gallery results in a more accurate ReID model, even for query samples with new outfits that do not include faces. Moreover, we claim that existing CC-ReID benchmarks do not fully represent real-world scenarios, and propose a new video CC-ReID dataset called 42Street, based on a theater play that includes crowded scenes and numerous clothes changes. When applied to multiple ReID models, our method (GEFF) achieves an average improvement of 33.5% and 6.7% in the Top-1 clothes-changing metric on the PRCC and LTCC benchmarks. Combined with the latest ReID models, our method achieves new SOTA results on the PRCC, LTCC, CCVID, LaST and VC-Clothes benchmarks and the proposed 42Street dataset.

Arnon Turetzky, Tzvi Michelson, Yossi Adi et al.

Convolutional neural networks contain strong priors for generating natural looking images [1]. These priors enable image denoising, super resolution, and inpainting in an unsupervised manner. Previous attempts to demonstrate similar ideas in audio, namely deep audio priors, (i) use hand picked architectures such as harmonic convolutions, (ii) only work with spectrogram input, and (iii) have been used mostly for eliminating Gaussian noise [2]. In this work we show that existing SOTA architectures for audio source separation contain deep priors even when working with the raw waveform. Deep priors can be discovered by training a neural network to generate a single corrupted signal when given white noise as input. A network with relevant deep priors is likely to generate a cleaner version of the signal before converging on the corrupted signal. We demonstrate this restoration effect with several corruptions: background noise, reverberations, and a gap in the signal (audio inpainting).

Matan Levy, Ran Margolin, Bar Cavia et al.

We introduce LiveSVG, a zero-shot approach for generating Scalable Vector Graphics (SVG) animations using video diffusion models. Current SVG animation methods struggle with complex motions: LLM-based code synthesis fails to express fine, non-rigid Bézier deformations, while Score Distillation Sampling (SDS) provides noisy gradients and often requires category-specific priors like skeletons. In contrast, LiveSVG fits vector geometry directly to an explicitly generated target video. Given an input SVG image and a motion prompt, we generate a previewable target video using a frozen image-to-video model, then fit the original SVG to this video via differentiable rendering. Our fitting stage is skeleton-free, utilizing a dual-level motion representation that combines per-group homographies for coarse articulation with per-path Bézier control-point offsets for local deformations. To resolve color-induced correspondence ambiguities during pixel-wise fitting, we introduce a novel sphere-packing recolorization strategy. We also present ChallengeSVG, a benchmark of complex, multi-object scenes that exposes the limitations of prior work. Evaluations demonstrate that LiveSVG significantly outperforms existing methods on both AniClipart and ChallengeSVG, establishing direct reference-video fitting as a practical, robust route to prompt-aligned and fully editable vector animation.

Tzvi Michelson, Hillel Aviezer, Shmuel Peleg

Despite much progress in the field of facial expression recognition, little attention has been paid to the recognition of peak emotion. Aviezer et al. [1] showed that humans have trouble discerning between positive and negative peak emotions. In this work we analyze how deep learning fares on this challenge. We find that (i) despite using very small datasets, features extracted from deep learning models can achieve results significantly better than humans. (ii) We find that deep learning models, even when trained only on datasets tagged by humans, still outperform humans in this task.

Asaf Joseph, Shmuel Peleg

Clothes-Changing Person Re-Identification (ReID) aims to recognize the same individual across different videos captured at various times and locations. This task is particularly challenging due to changes in appearance, such as clothing, hairstyle, and accessories. We propose a Clothes-Changing ReID method that uses only skeleton data and does not use appearance features. Traditional ReID methods often depend on appearance features, leading to decreased accuracy when clothing changes. Our approach utilizes a spatio-temporal Graph Convolution Network (GCN) encoder to generate a skeleton-based descriptor for each individual. During testing, we improve accuracy by aggregating predictions from multiple segments of a video clip. Evaluated on the CCVID dataset with several different pose estimation models, our method achieves state-of-the-art performance, offering a robust and efficient solution for Clothes-Changing ReID.

Tzvi Michelson, Shmuel Peleg

What makes a talk successful? Is it the content or the presentation? We try to estimate the contribution of the speaker's oratory skills to the talk's success, while ignoring the content of the talk. By oratory skills we refer to facial expressions, motions and gestures, as well as the vocal features. We use TED Talks as our dataset, and measure the success of each talk by its view count. Using this dataset we train a neural network to assess the oratory skills in a talk through three factors: body pose, facial expressions, and acoustic features. Most previous work on automatic evaluation of oratory skills uses hand-crafted expert annotations for both the quality of the talk and for the identification of predefined actions. Unlike prior art, we measure the quality to be equivalent to the view count of the talk as counted by TED, and allow the network to automatically learn the actions, expressions, and sounds that are relevant to the success of a talk. We find that oratory skills alone contribute substantially to the chances of a talk being successful.

Avital Shafran, Shmuel Peleg, Yedid Hoshen

Membership inference attacks (MIA) try to detect if data samples were used to train a neural network model, e.g. to detect copyright abuses. We show that models with higher dimensional input and output are more vulnerable to MIA, and address in more detail models for image translation and semantic segmentation, including medical image segmentation. We show that reconstruction-errors can lead to very effective MIA attacks as they are indicative of memorization. Unfortunately, reconstruction error alone is less effective at discriminating between non-predictable images used in training and easy to predict images that were never seen before. To overcome this, we propose using a novel predictability error that can be computed for each sample, and its computation does not require a training set. Our membership error, obtained by subtracting the predictability error from the reconstruction error, is shown to achieve high MIA accuracy on an extensive number of benchmarks.

Avital Shafran, Gil Segev, Shmuel Peleg et al.

As neural networks revolutionize many applications, significant privacy conflicts between model users and providers emerge. The cryptography community developed a variety of techniques for secure computation to address such privacy issues. As generic techniques for secure computation are typically prohibitively ineffective, many efforts focus on optimizing their underlying cryptographic tools. Differently, we propose to optimize the initial design of crypto-oriented neural architectures and provide a novel Partial Activation layer. The proposed layer is much faster for secure computation. Evaluating our method on three state-of-the-art architectures (SqueezeNet, ShuffleNetV2, and MobileNetV2) demonstrates significant improvement to the efficiency of secure inference on common evaluation metrics.

Tavi Halperin, Ariel Ephrat, Shmuel Peleg

Many speech segments in movies are re-recorded in a studio during postproduction, to compensate for poor sound quality as recorded on location. Manual alignment of the newly-recorded speech with the original lip movements is a tedious task. We present an audio-to-video alignment method for automating speech to lips alignment, stretching and compressing the audio signal to match the lip movements. This alignment is based on deep audio-visual features, mapping the lips video and the speech signal to a shared representation. Using this shared representation we compute the lip-sync error between every short speech period and every video frame, followed by the determination of the optimal corresponding frame for each short sound period over the entire video clip. We demonstrate successful alignment both quantitatively, using a human perception-inspired metric, as well as qualitatively. The strongest advantage of our audio-to-video approach is in cases where the original voice in unclear, and where a constant shift of the sound can not give a perfect alignment. In these cases state-of-the-art methods will fail.

Aviv Gabbay, Asaph Shamir, Shmuel Peleg

When video is shot in noisy environment, the voice of a speaker seen in the video can be enhanced using the visible mouth movements, reducing background noise. While most existing methods use audio-only inputs, improved performance is obtained with our visual speech enhancement, based on an audio-visual neural network. We include in the training data videos to which we added the voice of the target speaker as background noise. Since the audio input is not sufficient to separate the voice of a speaker from his own voice, the trained model better exploits the visual input and generalizes well to different noise types. The proposed model outperforms prior audio visual methods on two public lipreading datasets. It is also the first to be demonstrated on a dataset not designed for lipreading, such as the weekly addresses of Barack Obama.

Aviv Gabbay, Ariel Ephrat, Tavi Halperin et al.

Isolating the voice of a specific person while filtering out other voices or background noises is challenging when video is shot in noisy environments. We propose audio-visual methods to isolate the voice of a single speaker and eliminate unrelated sounds. First, face motions captured in the video are used to estimate the speaker's voice, by passing the silent video frames through a video-to-speech neural network-based model. Then the speech predictions are applied as a filter on the noisy input audio. This approach avoids using mixtures of sounds in the learning process, as the number of such possible mixtures is huge, and would inevitably bias the trained model. We evaluate our method on two audio-visual datasets, GRID and TCD-TIMIT, and show that our method attains significant SDR and PESQ improvements over the raw video-to-speech predictions, and a well-known audio-only method.

Ariel Ephrat, Tavi Halperin, Shmuel Peleg

Speechreading is the task of inferring phonetic information from visually observed articulatory facial movements, and is a notoriously difficult task for humans to perform. In this paper we present an end-to-end model based on a convolutional neural network (CNN) for generating an intelligible and natural-sounding acoustic speech signal from silent video frames of a speaking person. We train our model on speakers from the GRID and TCD-TIMIT datasets, and evaluate the quality and intelligibility of reconstructed speech using common objective measurements. We show that speech predictions from the proposed model attain scores which indicate significantly improved quality over existing models. In addition, we show promising results towards reconstructing speech from an unconstrained dictionary.

Ariel Ephrat, Shmuel Peleg

Speechreading is a notoriously difficult task for humans to perform. In this paper we present an end-to-end model based on a convolutional neural network (CNN) for generating an intelligible acoustic speech signal from silent video frames of a speaking person. The proposed CNN generates sound features for each frame based on its neighboring frames. Waveforms are then synthesized from the learned speech features to produce intelligible speech. We show that by leveraging the automatic feature learning capabilities of a CNN, we can obtain state-of-the-art word intelligibility on the GRID dataset, and show promising results for learning out-of-vocabulary (OOV) words.

Yoni Kasten, Gil Ben-Artzi, Shmuel Peleg et al.

Computing the epipolar geometry between cameras with very different viewpoints is often very difficult. The appearance of objects can vary greatly, and it is difficult to find corresponding feature points. Prior methods searched for corresponding epipolar lines using points on the convex hull of the silhouette of a single moving object. These methods fail when the scene includes multiple moving objects. This paper extends previous work to scenes having multiple moving objects by using the "Motion Barcodes", a temporal signature of lines. Corresponding epipolar lines have similar motion barcodes, and candidate pairs of corresponding epipoar lines are found by the similarity of their motion barcodes. As in previous methods we assume that cameras are relatively stationary and that moving objects have already been extracted using background subtraction.

Tavi Halperin, Yair Poleg, Chetan Arora et al.

The possibility of sharing one's point of view makes use of wearable cameras compelling. These videos are often long, boring and coupled with extreme shake, as the camera is worn on a moving person. Fast forwarding (i.e. frame sampling) is a natural choice for quick video browsing. However, this accentuates the shake caused by natural head motion in an egocentric video, making the fast forwarded video useless. We propose EgoSampling, an adaptive frame sampling that gives stable, fast forwarded, hyperlapse videos. Adaptive frame sampling is formulated as an energy minimization problem, whose optimal solution can be found in polynomial time. We further turn the camera shake from a drawback into a feature, enabling the increase in field-of-view of the output video. This is obtained when each output frame is mosaiced from several input frames. The proposed technique also enables the generation of a single hyperlapse video from multiple egocentric videos, allowing even faster video consumption.

Gil Ben-Artzi, Tavi Halperin, Michael Werman et al.

It is known that epipolar geometry can be computed from three epipolar line correspondences but this computation is rarely used in practice since there are no simple methods to find corresponding lines. Instead, methods for finding corresponding points are widely used. This paper proposes a similarity measure between lines that indicates whether two lines are corresponding epipolar lines and enables finding epipolar line correspondences as needed for the computation of epipolar geometry. A similarity measure between two lines, suitable for video sequences of a dynamic scene, has been previously described. This paper suggests a stereo matching similarity measure suitable for images. It is based on the quality of stereo matching between the two lines, as corresponding epipolar lines yield a good stereo correspondence. Instead of an exhaustive search over all possible pairs of lines, the search space is substantially reduced when two corresponding point pairs are given. We validate the proposed method using real-world images and compare it to state-of-the-art methods. We found this method to be more accurate by a factor of five compared to the standard method using seven corresponding points and comparable to the 8-points algorithm.

Gil Ben-Artzi, Yoni Kasten, Shmuel Peleg et al.

Computing the epipolar geometry between cameras with very different viewpoints is often problematic as matching points are hard to find. In these cases, it has been proposed to use information from dynamic objects in the scene for suggesting point and line correspondences. We propose a speed up of about two orders of magnitude, as well as an increase in robustness and accuracy, to methods computing epipolar geometry from dynamic silhouettes. This improvement is based on a new temporal signature: motion barcode for lines. Motion barcode is a binary temporal sequence for lines, indicating for each frame the existence of at least one foreground pixel on that line. The motion barcodes of two corresponding epipolar lines are very similar, so the search for corresponding epipolar lines can be limited only to lines having similar barcodes. The use of motion barcodes leads to increased speed, accuracy, and robustness in computing the epipolar geometry.

Yedid Hoshen, Shmuel Peleg

A simple Neural Network model is presented for end-to-end visual learning of arithmetic operations from pictures of numbers. The input consists of two pictures, each showing a 7-digit number. The output, also a picture, displays the number showing the result of an arithmetic operation (e.g., addition or subtraction) on the two input numbers. The concepts of a number, or of an operator, are not explicitly introduced. This indicates that addition is a simple cognitive task, which can be learned visually using a very small number of neurons. Other operations, e.g., multiplication, were not learnable using this architecture. Some tasks were not learnable end-to-end (e.g., addition with Roman numerals), but were easily learnable once broken into two separate sub-tasks: a perceptual \textit{Character Recognition} and cognitive \textit{Arithmetic} sub-tasks. This indicates that while some tasks may be easily learnable end-to-end, other may need to be broken into sub-tasks.

Yedid Hoshen, Shmuel Peleg

Video surveillance cameras generate most of recorded video, and there is far more recorded video than operators can watch. Much progress has recently been made using summarization of recorded video, but such techniques do not have much impact on live video surveillance. We assume a camera hierarchy where a Master camera observes the decision-critical region, and one or more Slave cameras observe regions where past activity is important for making the current decision. We propose that when people appear in the live Master camera, the Slave cameras will display their past activities, and the operator could use past information for real-time decision making. The basic units of our method are action tubes, representing objects and their trajectories over time. Our object-based method has advantages over frame based methods, as it can handle multiple people, multiple activities for each person, and can address re-identification uncertainty.

Yair Poleg, Ariel Ephrat, Shmuel Peleg et al.

While egocentric video is becoming increasingly popular, browsing it is very difficult. In this paper we present a compact 3D Convolutional Neural Network (CNN) architecture for long-term activity recognition in egocentric videos. Recognizing long-term activities enables us to temporally segment (index) long and unstructured egocentric videos. Existing methods for this task are based on hand tuned features derived from visible objects, location of hands, as well as optical flow. Given a sparse optical flow volume as input, our CNN classifies the camera wearer's activity. We obtain classification accuracy of 89%, which outperforms the current state-of-the-art by 19%. Additional evaluation is performed on an extended egocentric video dataset, classifying twice the amount of categories than current state-of-the-art. Furthermore, our CNN is able to recognize whether a video is egocentric or not with 99.2% accuracy, up by 24% from current state-of-the-art. To better understand what the network actually learns, we propose a novel visualization of CNN kernels as flow fields.

Yair Poleg, Tavi Halperin, Chetan Arora et al.

While egocentric cameras like GoPro are gaining popularity, the videos they capture are long, boring, and difficult to watch from start to end. Fast forwarding (i.e. frame sampling) is a natural choice for faster video browsing. However, this accentuates the shake caused by natural head motion, making the fast forwarded video useless. We propose EgoSampling, an adaptive frame sampling that gives more stable fast forwarded videos. Adaptive frame sampling is formulated as energy minimization, whose optimal solution can be found in polynomial time. In addition, egocentric video taken while walking suffers from the left-right movement of the head as the body weight shifts from one leg to another. We turn this drawback into a feature: Stereo video can be created by sampling the frames from the left most and right most head positions of each step, forming approximate stereo-pairs.

Gil Ben-Artzi, Michael Werman, Shmuel Peleg

We introduce a simple and effective method for retrieval of videos showing a specific event, even when the videos of that event were captured from significantly different viewpoints. Appearance-based methods fail in such cases, as appearances change with large changes of viewpoints. Our method is based on a pixel-based feature, "motion barcode", which records the existence/non-existence of motion as a function of time. While appearance, motion magnitude, and motion direction can vary greatly between disparate viewpoints, the existence of motion is viewpoint invariant. Based on the motion barcode, a similarity measure is developed for videos of the same event taken from very different viewpoints. This measure is robust to occlusions common under different viewpoints, and can be computed efficiently. Event retrieval is demonstrated using challenging videos from stationary and hand held cameras.

Yedid Hoshen, Shmuel Peleg

Egocentric cameras are being worn by an increasing number of users, among them many security forces worldwide. GoPro cameras already penetrated the mass market, reporting substantial increase in sales every year. As head-worn cameras do not capture the photographer, it may seem that the anonymity of the photographer is preserved even when the video is publicly distributed. We show that camera motion, as can be computed from the egocentric video, provides unique identity information. The photographer can be reliably recognized from a few seconds of video captured when walking. The proposed method achieves more than 90% recognition accuracy in cases where the random success rate is only 3%. Applications can include theft prevention by locking the camera when not worn by its rightful owner. Searching video sharing services (e.g. YouTube) for egocentric videos shot by a specific photographer may also become possible. An important message in this paper is that photographers should be aware that sharing egocentric video will compromise their anonymity, even when their face is not visible.