Du Tran

Weiyao Wang, Matt Feiszli, Heng Wang et al.

Open-world instance segmentation is the task of grouping pixels into object instances without any pre-determined taxonomy. This is challenging, as state-of-the-art methods rely on explicit class semantics obtained from large labeled datasets, and out-of-domain evaluation performance drops significantly. Here we propose a novel approach for mask proposals, Generic Grouping Networks (GGNs), constructed without semantic supervision. Our approach combines a local measure of pixel affinity with instance-level mask supervision, producing a training regimen designed to make the model as generic as the data diversity allows. We introduce a method for predicting Pairwise Affinities (PA), a learned local relationship between pairs of pixels. PA generalizes very well to unseen categories. From PA we construct a large set of pseudo-ground-truth instance masks; combined with human-annotated instance masks we train GGNs and significantly outperform the SOTA on open-world instance segmentation on various benchmarks including COCO, LVIS, ADE20K, and UVO. Code is available on project website: https://sites.google.com/view/generic-grouping/.

Raghav Goyal, Effrosyni Mavroudi, Xitong Yang et al. · meta-ai

Video understanding tasks take many forms, from action detection to visual query localization and spatio-temporal grounding of sentences. These tasks differ in the type of inputs (only video, or video-query pair where query is an image region or sentence) and outputs (temporal segments or spatio-temporal tubes). However, at their core they require the same fundamental understanding of the video, i.e., the actors and objects in it, their actions and interactions. So far these tasks have been tackled in isolation with individual, highly specialized architectures, which do not exploit the interplay between tasks. In contrast, in this paper, we present a single, unified model for tackling query-based video understanding in long-form videos. In particular, our model can address all three tasks of the Ego4D Episodic Memory benchmark which entail queries of three different forms: given an egocentric video and a visual, textual or activity query, the goal is to determine when and where the answer can be seen within the video. Our model design is inspired by recent query-based approaches to spatio-temporal grounding, and contains modality-specific query encoders and task-specific sliding window inference that allow multi-task training with diverse input modalities and different structured outputs. We exhaustively analyze relationships among the tasks and illustrate that cross-task learning leads to improved performance on each individual task, as well as the ability to generalize to unseen tasks, such as zero-shot spatial localization of language queries.

Tarun Kalluri, Weiyao Wang, Heng Wang et al.

Many top-down architectures for instance segmentation achieve significant success when trained and tested on pre-defined closed-world taxonomy. However, when deployed in the open world, they exhibit notable bias towards seen classes and suffer from significant performance drop. In this work, we propose a novel approach for open world instance segmentation called bottom-Up and top-Down Open-world Segmentation (UDOS) that combines classical bottom-up segmentation algorithms within a top-down learning framework. UDOS first predicts parts of objects using a top-down network trained with weak supervision from bottom-up segmentations. The bottom-up segmentations are class-agnostic and do not overfit to specific taxonomies. The part-masks are then fed into affinity-based grouping and refinement modules to predict robust instance-level segmentations. UDOS enjoys both the speed and efficiency from the top-down architectures and the generalization ability to unseen categories from bottom-up supervision. We validate the strengths of UDOS on multiple cross-category as well as cross-dataset transfer tasks from 5 challenging datasets including MS-COCO, LVIS, ADE20k, UVO and OpenImages, achieving significant improvements over state-of-the-art across the board. Our code and models are available on our project page.

Du Tran, Jitendra Malik

We propose a new task of space-time semantic correspondence prediction in videos. Given a source video, a target video, and a set of space-time key-points in the source video, the task requires predicting a set of keypoints in the target video that are the semantic correspondences of the provided source keypoints. We believe that this task is important for fine-grain video understanding, potentially enabling applications such as activity coaching, sports analysis, robot imitation learning, and more. Our contributions in this paper are: (i) proposing a new task and providing annotations for space-time semantic correspondences on two existing benchmarks: Penn Action and Pouring; and (ii) presenting a comprehensive set of baselines and experiments to gain insights about the new problem. Our main finding is that the space-time semantic correspondence prediction problem is best approached jointly in space and time rather than in their decomposed sub-problems: time alignment and spatial correspondences.

Gedas Bertasius, Christoph Feichtenhofer, Du Tran et al.

Modern approaches for multi-person pose estimation in video require large amounts of dense annotations. However, labeling every frame in a video is costly and labor intensive. To reduce the need for dense annotations, we propose a PoseWarper network that leverages training videos with sparse annotations (every k frames) to learn to perform dense temporal pose propagation and estimation. Given a pair of video frames---a labeled Frame A and an unlabeled Frame B---we train our model to predict human pose in Frame A using the features from Frame B by means of deformable convolutions to implicitly learn the pose warping between A and B. We demonstrate that we can leverage our trained PoseWarper for several applications. First, at inference time we can reverse the application direction of our network in order to propagate pose information from manually annotated frames to unlabeled frames. This makes it possible to generate pose annotations for the entire video given only a few manually-labeled frames. Compared to modern label propagation methods based on optical flow, our warping mechanism is much more compact (6M vs 39M parameters), and also more accurate (88.7% mAP vs 83.8% mAP). We also show that we can improve the accuracy of a pose estimator by training it on an augmented dataset obtained by adding our propagated poses to the original manual labels. Lastly, we can use our PoseWarper to aggregate temporal pose information from neighboring frames during inference. This allows our system to achieve state-of-the-art pose detection results on the PoseTrack2017 and PoseTrack2018 datasets. Code has been made available at: https://github.com/facebookresearch/PoseWarper.

Lan Wang, Yujia Chen, Du Tran et al.

Long video understanding presents challenges due to the inherent high computational complexity and redundant temporal information. An effective representation for long videos must efficiently process such redundancy while preserving essential contents for downstream tasks. This paper introduces SEmantic Attention Learning (SEAL), a novel unified representation for long videos. To reduce computational complexity, long videos are decomposed into three distinct types of semantic entities: scenes, objects, and actions, allowing models to operate on a compact set of entities rather than a large number of frames or pixels. To further address redundancy, we propose an attention learning module that balances token relevance with diversity, formulated as a subset selection optimization problem. Our representation is versatile and applicable across various long video understanding tasks. Extensive experiments demonstrate that SEAL significantly outperforms state-of-the-art methods in video question answering and temporal grounding tasks across diverse benchmarks, including LVBench, MovieChat-1K, and Ego4D.

Ozgur Kara, Yujia Chen, Ming-Hsuan Yang et al.

We present Split-then-Merge (StM), a novel framework designed to enhance control in generative video composition and address its data scarcity problem. Unlike conventional methods relying on annotated datasets or handcrafted rules, StM splits a large corpus of unlabeled videos into dynamic foreground and background layers, then self-composes them to learn how dynamic subjects interact with diverse scenes. This process enables the model to learn the complex compositional dynamics required for realistic video generation. StM introduces a novel transformation-aware training pipeline that utilizes a multi-layer fusion and augmentation to achieve affordance-aware composition, alongside an identity-preservation loss that maintains foreground fidelity during blending. Experiments show StM outperforms SoTA methods in both quantitative benchmarks and in humans/VLLM-based qualitative evaluations. More details are available at our project page: https://split-then-merge.github.io

Jue Wang, Gedas Bertasius, Du Tran et al.

Video transformers have recently emerged as a competitive alternative to 3D CNNs for video understanding. However, due to their large number of parameters and reduced inductive biases, these models require supervised pretraining on large-scale image datasets to achieve top performance. In this paper, we empirically demonstrate that self-supervised pretraining of video transformers on video-only datasets can lead to action recognition results that are on par or better than those obtained with supervised pretraining on large-scale image datasets, even massive ones such as ImageNet-21K. Since transformer-based models are effective at capturing dependencies over extended temporal spans, we propose a simple learning procedure that forces the model to match a long-term view to a short-term view of the same video. Our approach, named Long-Short Temporal Contrastive Learning (LSTCL), enables video transformers to learn an effective clip-level representation by predicting temporal context captured from a longer temporal extent. To demonstrate the generality of our findings, we implement and validate our approach under three different self-supervised contrastive learning frameworks (MoCo v3, BYOL, SimSiam) using two distinct video-transformer architectures, including an improved variant of the Swin Transformer augmented with space-time attention. We conduct a thorough ablation study and show that LSTCL achieves competitive performance on multiple video benchmarks and represents a convincing alternative to supervised image-based pretraining.

Weiyao Wang, Matt Feiszli, Heng Wang et al.

Current state-of-the-art object detection and segmentation methods work well under the closed-world assumption. This closed-world setting assumes that the list of object categories is available during training and deployment. However, many real-world applications require detecting or segmenting novel objects, i.e., object categories never seen during training. In this paper, we present, UVO (Unidentified Video Objects), a new benchmark for open-world class-agnostic object segmentation in videos. Besides shifting the problem focus to the open-world setup, UVO is significantly larger, providing approximately 8 times more videos compared with DAVIS, and 7 times more mask (instance) annotations per video compared with YouTube-VOS and YouTube-VIS. UVO is also more challenging as it includes many videos with crowded scenes and complex background motions. We demonstrated that UVO can be used for other applications, such as object tracking and super-voxel segmentation, besides open-world object segmentation. We believe that UVo is a versatile testbed for researchers to develop novel approaches for open-world class-agnostic object segmentation, and inspires new research directions towards a more comprehensive video understanding beyond classification and detection.

Tarun Kalluri, Deepak Pathak, Manmohan Chandraker et al.

A majority of methods for video frame interpolation compute bidirectional optical flow between adjacent frames of a video, followed by a suitable warping algorithm to generate the output frames. However, approaches relying on optical flow often fail to model occlusions and complex non-linear motions directly from the video and introduce additional bottlenecks unsuitable for widespread deployment. We address these limitations with FLAVR, a flexible and efficient architecture that uses 3D space-time convolutions to enable end-to-end learning and inference for video frame interpolation. Our method efficiently learns to reason about non-linear motions, complex occlusions and temporal abstractions, resulting in improved performance on video interpolation, while requiring no additional inputs in the form of optical flow or depth maps. Due to its simplicity, FLAVR can deliver 3x faster inference speed compared to the current most accurate method on multi-frame interpolation without losing interpolation accuracy. In addition, we evaluate FLAVR on a wide range of challenging settings and consistently demonstrate superior qualitative and quantitative results compared with prior methods on various popular benchmarks including Vimeo-90K, UCF101, DAVIS, Adobe, and GoPro. Finally, we demonstrate that FLAVR for video frame interpolation can serve as a useful self-supervised pretext task for action recognition, optical flow estimation, and motion magnification.

Humam Alwassel, Dhruv Mahajan, Bruno Korbar et al.

Visual and audio modalities are highly correlated, yet they contain different information. Their strong correlation makes it possible to predict the semantics of one from the other with good accuracy. Their intrinsic differences make cross-modal prediction a potentially more rewarding pretext task for self-supervised learning of video and audio representations compared to within-modality learning. Based on this intuition, we propose Cross-Modal Deep Clustering (XDC), a novel self-supervised method that leverages unsupervised clustering in one modality (e.g., audio) as a supervisory signal for the other modality (e.g., video). This cross-modal supervision helps XDC utilize the semantic correlation and the differences between the two modalities. Our experiments show that XDC outperforms single-modality clustering and other multi-modal variants. XDC achieves state-of-the-art accuracy among self-supervised methods on multiple video and audio benchmarks. Most importantly, our video model pretrained on large-scale unlabeled data significantly outperforms the same model pretrained with full-supervision on ImageNet and Kinetics for action recognition on HMDB51 and UCF101. To the best of our knowledge, XDC is the first self-supervised learning method that outperforms large-scale fully-supervised pretraining for action recognition on the same architecture.

Linchao Zhu, Laura Sevilla-Lara, Du Tran et al.

Typical video classification methods often divide a video into short clips, do inference on each clip independently, then aggregate the clip-level predictions to generate the video-level results. However, processing visually similar clips independently ignores the temporal structure of the video sequence, and increases the computational cost at inference time. In this paper, we propose a novel framework named FASTER, i.e., Feature Aggregation for Spatio-TEmporal Redundancy. FASTER aims to leverage the redundancy between neighboring clips and reduce the computational cost by learning to aggregate the predictions from models of different complexities. The FASTER framework can integrate high quality representations from expensive models to capture subtle motion information and lightweight representations from cheap models to cover scene changes in the video. A new recurrent network (i.e., FAST-GRU) is designed to aggregate the mixture of different representations. Compared with existing approaches, FASTER can reduce the FLOPs by over 10x? while maintaining the state-of-the-art accuracy across popular datasets, such as Kinetics, UCF-101 and HMDB-51.

Yufei Wang, Du Tran, Lorenzo Torresani

Although a video is effectively a sequence of images, visual perception systems typically model images and videos separately, thus failing to exploit the correlation and the synergy provided by these two media. While a few prior research efforts have explored the benefits of leveraging still-image datasets for video analysis, or vice-versa, most of these attempts have been limited to pretraining a model on one type of visual modality and then adapting it via finetuning on the other modality. In contrast, in this paper we introduce a framework that enables joint training of a unified model on mixed collections of image and video examples spanning different tasks. The key ingredient in our architecture design is a new network block, which we name UniDual. It consists of a shared 2D spatial convolution followed by two parallel point-wise convolutional layers, one devoted to images and the other one used for videos. For video input, the point-wise filtering implements a temporal convolution. For image input, it performs a pixel-wise nonlinear transformation. Repeated stacking of such blocks gives rise to a network where images and videos undergo partially distinct execution pathways, unified by spatial convolutions (capturing commonalities in visual appearance) but separated by point-wise operations (modeling patterns specific to each modality). Extensive experiments on Kinetics and ImageNet demonstrate that our UniDual model jointly trained on these datasets yields substantial accuracy gains for both tasks, compared to 1) training separate models, 2) traditional multi-task learning and 3) the conventional framework of pretraining-followed-by-finetuning. On Kinetics, the UniDual architecture applied to a state-of-the-art video backbone model (R(2+1)D-152) yields an additional video@1 accuracy gain of 1.5%.

Heng Wang, Du Tran, Lorenzo Torresani et al.

Motion is a salient cue to recognize actions in video. Modern action recognition models leverage motion information either explicitly by using optical flow as input or implicitly by means of 3D convolutional filters that simultaneously capture appearance and motion information. This paper proposes an alternative approach based on a learnable correlation operator that can be used to establish frame-toframe matches over convolutional feature maps in the different layers of the network. The proposed architecture enables the fusion of this explicit temporal matching information with traditional appearance cues captured by 2D convolution. Our correlation network compares favorably with widely-used 3D CNNs for video modeling, and achieves competitive results over the prominent two-stream network while being much faster to train. We empirically demonstrate that correlation networks produce strong results on a variety of video datasets, and outperform the state of the art on four popular benchmarks for action recognition: Kinetics, Something-Something, Diving48 and Sports1M.

Weiyao Wang, Du Tran, Matt Feiszli

Consider end-to-end training of a multi-modal vs. a single-modal network on a task with multiple input modalities: the multi-modal network receives more information, so it should match or outperform its single-modal counterpart. In our experiments, however, we observe the opposite: the best single-modal network always outperforms the multi-modal network. This observation is consistent across different combinations of modalities and on different tasks and benchmarks. This paper identifies two main causes for this performance drop: first, multi-modal networks are often prone to overfitting due to increased capacity. Second, different modalities overfit and generalize at different rates, so training them jointly with a single optimization strategy is sub-optimal. We address these two problems with a technique we call Gradient Blending, which computes an optimal blend of modalities based on their overfitting behavior. We demonstrate that Gradient Blending outperforms widely-used baselines for avoiding overfitting and achieves state-of-the-art accuracy on various tasks including human action recognition, ego-centric action recognition, and acoustic event detection.

Deepti Ghadiyaram, Matt Feiszli, Du Tran et al.

Current fully-supervised video datasets consist of only a few hundred thousand videos and fewer than a thousand domain-specific labels. This hinders the progress towards advanced video architectures. This paper presents an in-depth study of using large volumes of web videos for pre-training video models for the task of action recognition. Our primary empirical finding is that pre-training at a very large scale (over 65 million videos), despite on noisy social-media videos and hashtags, substantially improves the state-of-the-art on three challenging public action recognition datasets. Further, we examine three questions in the construction of weakly-supervised video action datasets. First, given that actions involve interactions with objects, how should one construct a verb-object pre-training label space to benefit transfer learning the most? Second, frame-based models perform quite well on action recognition; is pre-training for good image features sufficient or is pre-training for spatio-temporal features valuable for optimal transfer learning? Finally, actions are generally less well-localized in long videos vs. short videos; since action labels are provided at a video level, how should one choose video clips for best performance, given some fixed budget of number or minutes of videos?

Bruno Korbar, Du Tran, Lorenzo Torresani

While many action recognition datasets consist of collections of brief, trimmed videos each containing a relevant action, videos in the real-world (e.g., on YouTube) exhibit very different properties: they are often several minutes long, where brief relevant clips are often interleaved with segments of extended duration containing little change. Applying densely an action recognition system to every temporal clip within such videos is prohibitively expensive. Furthermore, as we show in our experiments, this results in suboptimal recognition accuracy as informative predictions from relevant clips are outnumbered by meaningless classification outputs over long uninformative sections of the video. In this paper we introduce a lightweight "clip-sampling" model that can efficiently identify the most salient temporal clips within a long video. We demonstrate that the computational cost of action recognition on untrimmed videos can be dramatically reduced by invoking recognition only on these most salient clips. Furthermore, we show that this yields significant gains in recognition accuracy compared to analysis of all clips or randomly/uniformly selected clips. On Sports1M, our clip sampling scheme elevates the accuracy of an already state-of-the-art action classifier by 7% and reduces by more than 15 times its computational cost.

Du Tran, Heng Wang, Lorenzo Torresani et al.

Group convolution has been shown to offer great computational savings in various 2D convolutional architectures for image classification. It is natural to ask: 1) if group convolution can help to alleviate the high computational cost of video classification networks; 2) what factors matter the most in 3D group convolutional networks; and 3) what are good computation/accuracy trade-offs with 3D group convolutional networks. This paper studies the effects of different design choices in 3D group convolutional networks for video classification. We empirically demonstrate that the amount of channel interactions plays an important role in the accuracy of 3D group convolutional networks. Our experiments suggest two main findings. First, it is a good practice to factorize 3D convolutions by separating channel interactions and spatiotemporal interactions as this leads to improved accuracy and lower computational cost. Second, 3D channel-separated convolutions provide a form of regularization, yielding lower training accuracy but higher test accuracy compared to 3D convolutions. These two empirical findings lead us to design an architecture -- Channel-Separated Convolutional Network (CSN) -- which is simple, efficient, yet accurate. On Sports1M, Kinetics, and Something-Something, our CSNs are comparable with or better than the state-of-the-art while being 2-3 times more efficient.

Rohit Girdhar, Du Tran, Lorenzo Torresani et al.

Video recognition models have progressed significantly over the past few years, evolving from shallow classifiers trained on hand-crafted features to deep spatiotemporal networks. However, labeled video data required to train such models have not been able to keep up with the ever-increasing depth and sophistication of these networks. In this work, we propose an alternative approach to learning video representations that require no semantically labeled videos and instead leverages the years of effort in collecting and labeling large and clean still-image datasets. We do so by using state-of-the-art models pre-trained on image datasets as "teachers" to train video models in a distillation framework. We demonstrate that our method learns truly spatiotemporal features, despite being trained only using supervision from still-image networks. Moreover, it learns good representations across different input modalities, using completely uncurated raw video data sources and with different 2D teacher models. Our method obtains strong transfer performance, outperforming standard techniques for bootstrapping video architectures with image-based models by 16%. We believe that our approach opens up new approaches for learning spatiotemporal representations from unlabeled video data.

Gedas Bertasius, Christoph Feichtenhofer, Du Tran et al.

Despite huge success in the image domain, modern detection models such as Faster R-CNN have not been used nearly as much for video analysis. This is arguably due to the fact that detection models are designed to operate on single frames and as a result do not have a mechanism for learning motion representations directly from video. We propose a learning procedure that allows detection models such as Faster R-CNN to learn motion features directly from the RGB video data while being optimized with respect to a pose estimation task. Given a pair of video frames---Frame A and Frame B---we force our model to predict human pose in Frame A using the features from Frame B. We do so by leveraging deformable convolutions across space and time. Our network learns to spatially sample features from Frame B in order to maximize pose detection accuracy in Frame A. This naturally encourages our network to learn motion offsets encoding the spatial correspondences between the two frames. We refer to these motion offsets as DiMoFs (Discriminative Motion Features). In our experiments we show that our training scheme helps learn effective motion cues, which can be used to estimate and localize salient human motion. Furthermore, we demonstrate that as a byproduct, our model also learns features that lead to improved pose detection in still-images, and better keypoint tracking. Finally, we show how to leverage our learned model for the tasks of spatiotemporal action localization and fine-grained action recognition.

Bruno Korbar, Du Tran, Lorenzo Torresani

There is a natural correlation between the visual and auditive elements of a video. In this work we leverage this connection to learn general and effective models for both audio and video analysis from self-supervised temporal synchronization. We demonstrate that a calibrated curriculum learning scheme, a careful choice of negative examples, and the use of a contrastive loss are critical ingredients to obtain powerful multi-sensory representations from models optimized to discern temporal synchronization of audio-video pairs. Without further finetuning, the resulting audio features achieve performance superior or comparable to the state-of-the-art on established audio classification benchmarks (DCASE2014 and ESC-50). At the same time, our visual subnet provides a very effective initialization to improve the accuracy of video-based action recognition models: compared to learning from scratch, our self-supervised pretraining yields a remarkable gain of +19.9% in action recognition accuracy on UCF101 and a boost of +17.7% on HMDB51.

Rohit Girdhar, Georgia Gkioxari, Lorenzo Torresani et al.

This paper addresses the problem of estimating and tracking human body keypoints in complex, multi-person video. We propose an extremely lightweight yet highly effective approach that builds upon the latest advancements in human detection and video understanding. Our method operates in two-stages: keypoint estimation in frames or short clips, followed by lightweight tracking to generate keypoint predictions linked over the entire video. For frame-level pose estimation we experiment with Mask R-CNN, as well as our own proposed 3D extension of this model, which leverages temporal information over small clips to generate more robust frame predictions. We conduct extensive ablative experiments on the newly released multi-person video pose estimation benchmark, PoseTrack, to validate various design choices of our model. Our approach achieves an accuracy of 55.2% on the validation and 51.8% on the test set using the Multi-Object Tracking Accuracy (MOTA) metric, and achieves state of the art performance on the ICCV 2017 PoseTrack keypoint tracking challenge.

Du Tran, Heng Wang, Lorenzo Torresani et al.

In this paper we discuss several forms of spatiotemporal convolutions for video analysis and study their effects on action recognition. Our motivation stems from the observation that 2D CNNs applied to individual frames of the video have remained solid performers in action recognition. In this work we empirically demonstrate the accuracy advantages of 3D CNNs over 2D CNNs within the framework of residual learning. Furthermore, we show that factorizing the 3D convolutional filters into separate spatial and temporal components yields significantly advantages in accuracy. Our empirical study leads to the design of a new spatiotemporal convolutional block "R(2+1)D" which gives rise to CNNs that achieve results comparable or superior to the state-of-the-art on Sports-1M, Kinetics, UCF101 and HMDB51.

Du Tran, Jamie Ray, Zheng Shou et al.

Learning image representations with ConvNets by pre-training on ImageNet has proven useful across many visual understanding tasks including object detection, semantic segmentation, and image captioning. Although any image representation can be applied to video frames, a dedicated spatiotemporal representation is still vital in order to incorporate motion patterns that cannot be captured by appearance based models alone. This paper presents an empirical ConvNet architecture search for spatiotemporal feature learning, culminating in a deep 3-dimensional (3D) Residual ConvNet. Our proposed architecture outperforms C3D by a good margin on Sports-1M, UCF101, HMDB51, THUMOS14, and ASLAN while being 2 times faster at inference time, 2 times smaller in model size, and having a more compact representation.

Joost van Amersfoort, Anitha Kannan, Marc'Aurelio Ranzato et al.

In this work we propose a simple unsupervised approach for next frame prediction in video. Instead of directly predicting the pixels in a frame given past frames, we predict the transformations needed for generating the next frame in a sequence, given the transformations of the past frames. This leads to sharper results, while using a smaller prediction model. In order to enable a fair comparison between different video frame prediction models, we also propose a new evaluation protocol. We use generated frames as input to a classifier trained with ground truth sequences. This criterion guarantees that models scoring high are those producing sequences which preserve discriminative features, as opposed to merely penalizing any deviation, plausible or not, from the ground truth. Our proposed approach compares favourably against more sophisticated ones on the UCF-101 data set, while also being more efficient in terms of the number of parameters and computational cost.

Du Tran, Maksim Bolonkin, Manohar Paluri et al.

While there is overall agreement that future technology for organizing, browsing and searching videos hinges on the development of methods for high-level semantic understanding of video, so far no consensus has been reached on the best way to train and assess models for this task. Casting video understanding as a form of action or event categorization is problematic as it is not fully clear what the semantic classes or abstractions in this domain should be. Language has been exploited to sidestep the problem of defining video categories, by formulating video understanding as the task of captioning or description. However, language is highly complex, redundant and sometimes ambiguous. Many different captions may express the same semantic concept. To account for this ambiguity, quantitative evaluation of video description requires sophisticated metrics, whose performance scores are typically hard to interpret by humans. This paper provides four contributions to this problem. First, we formulate Video Multiple Choice Caption (VideoMCC) as a new well-defined task with an easy-to-interpret performance measure. Second, we describe a general semi-automatic procedure to create benchmarks for this task. Third, we publicly release a large-scale video benchmark created with an implementation of this procedure and we include a human study that assesses human performance on our dataset. Finally, we propose and test a varied collection of approaches on this benchmark for the purpose of gaining a better understanding of the new challenges posed by video comprehension.

Du Tran, Lubomir Bourdev, Rob Fergus et al.

Over the last few years deep learning methods have emerged as one of the most prominent approaches for video analysis. However, so far their most successful applications have been in the area of video classification and detection, i.e., problems involving the prediction of a single class label or a handful of output variables per video. Furthermore, while deep networks are commonly recognized as the best models to use in these domains, there is a widespread perception that in order to yield successful results they often require time-consuming architecture search, manual tweaking of parameters and computationally intensive pre-processing or post-processing methods. In this paper we challenge these views by presenting a deep 3D convolutional architecture trained end to end to perform voxel-level prediction, i.e., to output a variable at every voxel of the video. Most importantly, we show that the same exact architecture can be used to achieve competitive results on three widely different voxel-prediction tasks: video semantic segmentation, optical flow estimation, and video coloring. The three networks learned on these problems are trained from raw video without any form of preprocessing and their outputs do not require post-processing to achieve outstanding performance. Thus, they offer an efficient alternative to traditional and much more computationally expensive methods in these video domains.

Du Tran, Lubomir Bourdev, Rob Fergus et al.

We propose a simple, yet effective approach for spatiotemporal feature learning using deep 3-dimensional convolutional networks (3D ConvNets) trained on a large scale supervised video dataset. Our findings are three-fold: 1) 3D ConvNets are more suitable for spatiotemporal feature learning compared to 2D ConvNets; 2) A homogeneous architecture with small 3x3x3 convolution kernels in all layers is among the best performing architectures for 3D ConvNets; and 3) Our learned features, namely C3D (Convolutional 3D), with a simple linear classifier outperform state-of-the-art methods on 4 different benchmarks and are comparable with current best methods on the other 2 benchmarks. In addition, the features are compact: achieving 52.8% accuracy on UCF101 dataset with only 10 dimensions and also very efficient to compute due to the fast inference of ConvNets. Finally, they are conceptually very simple and easy to train and use.

Du Tran, Lorenzo Torresani

This paper introduces EXMOVES, learned exemplar-based features for efficient recognition of actions in videos. The entries in our descriptor are produced by evaluating a set of movement classifiers over spatial-temporal volumes of the input sequence. Each movement classifier is a simple exemplar-SVM trained on low-level features, i.e., an SVM learned using a single annotated positive space-time volume and a large number of unannotated videos. Our representation offers two main advantages. First, since our mid-level features are learned from individual video exemplars, they require minimal amount of supervision. Second, we show that simple linear classification models trained on our global video descriptor yield action recognition accuracy approaching the state-of-the-art but at orders of magnitude lower cost, since at test-time no sliding window is necessary and linear models are efficient to train and test. This enables scalable action recognition, i.e., efficient classification of a large number of different actions even in large video databases. We show the generality of our approach by building our mid-level descriptors from two different low-level feature representations. The accuracy and efficiency of the approach are demonstrated on several large-scale action recognition benchmarks.