CLIP (Contrastive Language-Image Pre-training) uses contrastive learning from noise image-text pairs to excel at recognizing a wide array of candidates, yet its focus on broad associations hinders the precision in distinguishing subtle differences among fine-grained items. Conversely, Multimodal Large Language Models (MLLMs) excel at classifying fine-grained categories, thanks to their substantial knowledge from pre-training on web-level corpora. However, the performance of MLLMs declines with an increase in category numbers, primarily due to growing complexity and constraints of limited context window size. To synergize the strengths of both approaches and enhance the few-shot/zero-shot recognition abilities for datasets characterized by extensive and fine-grained vocabularies, this paper introduces RAR, a Retrieving And Ranking augmented method for MLLMs. We initially establish a multi-modal retriever based on CLIP to create and store explicit memory for different categories beyond the immediate context window. During inference, RAR retrieves the top- $k$ similar results from the memory and uses MLLMs to rank and make the final predictions. Our proposed approach not only addresses the inherent limitations in fine-grained recognition but also preserves the model's comprehensive knowledge base, significantly boosting accuracy across a range of vision-language recognition tasks. Notably, our approach demonstrates a significant improvement in performance on 5 fine-grained visual recognition benchmarks, 11 few-shot image recognition datasets, and the 2 object detection datasets under the zero-shot recognition setting.

We propose a new transformer-based image and video tokenizer with Binary Spherical Quantization (BSQ). BSQ projects the high-dimensional visual embedding to a lower-dimensional hypersphere and then applies binary quantization. BSQ is (1) parameter-efficient without an explicit codebook, (2) scalable to arbitrary token dimensions, and (3) compact: compressing visual data by up to 100× with minimal distortion. Our tokenizer uses a transformer encoder and decoder with simple block-wise causal masking to support variable-length videos as input. The resulting BSQ-ViT achieves state-of-the-art visual reconstruction quality on image and video reconstruction benchmarks with 2.4× throughput compared to the best prior methods. Furthermore, by learning an autoregressive prior for adaptive arithmetic coding, BSQ-ViT achieves comparable visual compression results with commonly used compression standards, e.g. JPEG2000/WebP for images and H.264/H.265 for videos. BSQ-ViT also enables masked language models to achieve competitive image synthesis quality to GAN and diffusion approaches.

Visual preference alignment involves training Large Vision-Language Models (LVLMs) to predict human preferences between visual inputs. This is typically achieved by using labeled datasets of chosen/rejected pairs and employing optimization algorithms like direct preference optimization (DPO). Existing visual alignment methods, primarily designed for single-image scenarios, struggle to effectively handle the complexity of multi-image tasks due to the scarcity of diverse training data and the high cost of annotating chosen/rejected pairs. We present Multi-Image Augmented Direct Preference Optimization (MIA-DPO), a visual preference alignment approach that effectively handles multi-image inputs. MIA-DPO mitigates the scarcity of diverse multi-image training data by extending single-image data with unrelated images arranged in grid collages or pic-in-pic formats, significantly reducing the costs associated with multi-image data annotations. Our observation reveals that attention values of LVLMs vary considerably across different images. We use attention values to identify and filter out rejected responses the model may have mistakenly focused on. Our attention-aware selection for constructing the chosen/rejected pairs without relying on (i) human annotation, (ii) extra data, and (iii) external models or APIs. MIA-DPO is compatible with various architectures and outperforms existing methods on five multi-image benchmarks, achieving an average performance boost of 3.0% on LLaVA-v1.5 and 4.3% on the recent InternLM-XC2.5. Moreover, MIA-DPO has a minimal effect on the model's ability to understand single images.

Contrastive Language-Image Pre-training (CLIP) plays an essential role in extracting valuable content information from images across diverse tasks. It aligns textual and visual modalities to comprehend the entire image, including all the details, even those irrelevant to specific tasks. How-ever, for a finer understanding and controlled editing of images, it becomes crucial to focus on specific regions of interest, which can be indicated as points, masks, or boxes by humans or perception models. To fulfill the require we introduce Alpha-CLIp, an enhanced version of CLIP with an auxiliary alpha channel to suggest attentive regions and fine-tuned with constructed millions of RGBA region-text pairs. Alpha-CLIP not only preserves the visual recognition ability of CLIP but also enables precise control over the emphasis of image contents. It demonstrates effectiveness in various tasks, including but not limited to open-world recognition, multimodal large language models, and conditional 2D / 3D generation. It has a strong potential to serve as a versatile tool for image-related tasks. Our project is with codes and models available is linked to https://aleafy.github.io/alpha-clip/.

Generating natural and meaningful responses to communicate with multi-modal human inputs is a fundamental capability of Large Vision-Language Models (LVLMs). While current open-source LVLMs demonstrate promising performance in simplified scenarios such as single-turn single-image input, they fall short in real-world conversation scenarios such as following instructions in a long context history with multi-turn and multi-images. Existing LVLM benchmarks primarily focus on single-choice questions or short-form responses, which do not adequately assess the capabilities of LVLMs in real-world human-AI interaction applications. Therefore, we introduce MMDU, a comprehensive benchmark, and MMDU-45k, a large-scale instruction tuning dataset, designed to evaluate and improve LVLMs' abilities in multi-turn and multi-image conversations. We employ the clustering algorithm to find the relevant images and textual descriptions from the open-source Wikipedia and construct the question-answer pairs by human annotators with the assistance of the GPT-4o model.MMDU has a maximum of 18k image+text tokens, 20 images, and 27 turns, which is at least 5x longer than previous benchmarks and poses challenges to current LVLMs. Our in-depth analysis of 15 representative LVLMs using MMDU reveals that open-source LVLMs lag behind closed-source counterparts due to limited conversational instruction tuning data.We demonstrate that fine-tuning open-source LVLMs on MMDU-45k significantly address this gap, generating longer and more accurate conversations, and improving scores on MMDU and existing benchmarks (MMStar: +1.1%, MathVista: +1.5%, ChartQA: +1.2%). Our contributions pave the way for bridging the gap between current LVLM models and real-world application demands. The links to MMDU, and MMDU-45k are available in the supplementary material.

We present a generative dialogue system capable of operating in a full-duplex manner, allowing for seamless interaction. It is based on a large language model (LLM) carefully aligned to be aware of a perception module, a motor function module, and the concept of a simple finite state machine (called neural FSM) with two states. The perception and motor function modules operate in tandem, allowing the system to speak and listen to the user simultaneously. The LLM generates textual tokens for inquiry responses and makes autonomous decisions to start responding to, wait for, or interrupt the user by emitting control tokens to the neural FSM. All these tasks of the LLM are carried out as next token prediction on a serialized view of the dialogue in real-time. In automatic quality evaluations simulating real-life interaction, the proposed system reduces the average conversation response latency by more than threefold compared with LLM-based half-duplex dialogue systems while responding within less than 500 milliseconds in more than 50% of evaluated interactions. Running an LLM with only 8 billion parameters, our system exhibits an 8% higher interruption precision rate than the best available commercial LLM for voice-based dialogue.

Negative flips are errors introduced in a classification system when a legacy model is updated. Existing methods to reduce the negative flip rate (NFR) either do so at the expense of overall accuracy by forcing a new model to imitate the old models, or use ensembles, which multiply inference cost prohibitively. We analyze the role of ensembles in reducing NFR and observe that they remove negative flips that are typically not close to the decision boundary, but often exhibit large deviations in the distance among their logits. Based on the observation, we present a method, called Ensemble Logit Difference Inhibition (ELODI), to train a classification system that achieves paragon performance in both error rate and NFR, at the inference cost of a single model. The method distills a homogeneous ensemble to a single student model which is used to update the classification system. ELODI also introduces a generalized distillation objective, Logit Difference Inhibition (LDI), which only penalizes the logit difference of a subset of classes with the highest logit values. On multiple image classification benchmarks, model updates with ELODI demonstrate superior accuracy retention and NFR reduction.

The common implementation of face recognition systems as a cascade of a detection stage and a recognition or verification stage can cause problems beyond failures of the detector. When the detector succeeds, it can detect faces that cannot be recognized, no matter how capable the recognition system is. Recognizability, a latent variable, should therefore be factored into the design and implementation of face recognition systems. We propose a measure of recognizability of a face image that leverages a key empirical observation: An embedding of face images, implemented by a deep neural network trained using mostly recognizable identities, induces a partition of the hypersphere whereby unrecognizable identities cluster together. This occurs regardless of the phenomenon that causes a face to be unrecognizable, be it optical or motion blur, partial occlusion, spatial quantization, or poor illumination. Therefore, we use the distance from such an "unrecognizable identity" as a measure of recognizability, and incorporate it into the design of the overall system. We show that accounting for recognizability reduces the error rate of single-image face recognition by 58% at FAR=1e-5 on the IJB-C Covariate Verification benchmark, and reduces the verification error rate by 24% at FAR=1e-5 in set-based recognition on the IJB-C benchmark.

We propose an online tracking algorithm that performs the object detection and data association under a common framework, capable of linking objects after a long time span. This is realized by preserving a large spatio-temporal memory to store the identity embeddings of the tracked objects, and by adaptively referencing and aggregating useful information from the memory as needed. Our model, called MeMOT, consists of three main modules that are all Transformer-based: 1) Hypothesis Generation that produce object proposals in the current video frame; 2) Memory Encoding that extracts the core information from the memory for each tracked object; and 3) Memory Decoding that solves the object detection and data association tasks simultaneously for multi-object tracking. When evaluated on widely adopted MOT benchmark datasets, MeMOT observes very competitive performance.

We propose a memory efficient method, named Stochastic Backpropagation (SBP), for training deep neural networks on videos. It is based on the finding that gradients from incomplete execution for backpropagation can still effectively train the models with minimal accuracy loss, which attributes to the high redundancy of video. SBP keeps all forward paths but randomly and independently removes the backward paths for each network layer in each training step. It reduces the GPU memory cost by eliminating the need to cache activation values corresponding to the dropped backward paths, whose amount can be controlled by an adjustable keep-ratio. Experiments show that SBP can be applied to a wide range of models for video tasks, leading to up to 80.0% GPU memory saving and 10% training speedup with less than 1% accuracy drop on action recognition and temporal action detection.

We propose TubeR: a simple solution for spatio-temporal video action detection. Different from existing methods that depend on either an offline actor detector or hand-designed actor-positional hypotheses like proposals or anchors, we propose to directly detect an action tubelet in a video by simultaneously performing action localization and recognition from a single representation. TubeR learns a set of tubelet-queries and utilizes a tubelet-attention module to model the dynamic spatio-temporal nature of a video clip, which effectively reinforces the model capacity compared to using actor-positional hypotheses in the spatio-temporal space. For videos containing transitional states or scene changes, we propose a context aware classification head to utilize short-term and long-term context to strengthen action classification, and an action switch regression head for detecting the precise temporal action extent. TubeR directly produces action tubelets with variable lengths and even maintains good results for long video clips. TubeR outperforms the previous state-of-the-art on commonly used action detection datasets AVA, UCF101-24 and JHMDB51-21. Code will be available on GluonCV(https://cv.gluon.ai/).

Temporal action segmentation is a task to classify each frame in the video with an action label. However, it is quite expensive to annotate every frame in a large corpus of videos to construct a comprehensive supervised training dataset. Thus in this work we propose an unsupervised method, namely SSCAP, that operates on a corpus of unlabeled videos and predicts a likely set of temporal segments across the videos. SSCAP leverages Self-Supervised learning to extract distinguishable features and then applies a novel Co-occurrence Action Parsing algorithm to not only capture the correlation among sub-actions under-lying the structure of activities, but also estimate the temporal path of the sub-actions in an accurate and general way. We evaluate on both classic datasets (Breakfast, 50Sal-ads) and the emerging fine-grained action dataset (Fine-Gym) with more complex activity structures and similar sub-actions. Results show that SSCAP achieves state-of-the-art performance on all datasets and can even outperform some weakly-supervised approaches, demonstrating its effectiveness and generalizability.

Yuqing Xie, Yi-An Lai, Yuanjun Xiong, Yi Zhang, Stefano Soatto. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

We tackle the problem of visual search under resource constraints. Existing systems use the same embedding model to compute representations (embeddings) for the query and gallery images. Such systems inherently face a hard accuracy-efficiency trade-off: the embedding model needs to be large enough to ensure high accuracy, yet small enough to enable query-embedding computation on resource-constrained platforms. This trade-off could be mitigated if gallery embeddings are generated from a large model and query embeddings are extracted using a compact model. The key to building such a system is to ensure representation compatibility between the query and gallery models. In this paper, we address two forms of compatibility: One enforced by modifying the parameters of each model that computes the embeddings. The other by modifying the architectures that compute the embeddings, leading to compatibility-aware neural architecture search (Cmp-NAS). We test Cmp-NAS on challenging retrieval tasks for fashion images (DeepFashion2), and face images (IJB-C). Compared to ordinary (homogeneous) visual search using the largest embedding model (paragon), Cmp-NAS achieves 80-fold and 23-fold cost reduction while maintaining accuracy within 0.3% and 1.6% of the paragon on DeepFashion2 and IJB-C respectively.

Reducing inconsistencies in the behavior of different versions of an AI system can be as important in practice as reducing its overall error. In image classification, sample-wise inconsistencies appear as "negative flips": A new model incorrectly predicts the output for a test sample that was correctly classified by the old (reference) model. Positive-congruent (PC) training aims at reducing error rate while at the same time reducing negative flips, thus maximizing congruency with the reference model only on positive predictions, unlike model distillation. We propose a simple approach for PC training, Focal Distillation, which enforces congruence with the reference model by giving more weights to samples that were correctly classified. We also found that, if the reference model itself can be chosen as an ensemble of multiple deep neural networks, negative flips can be further reduced without affecting the new model’s accuracy.

We propose a hierarchical graph neural network (GNN) model that learns how to cluster a set of images into an unknown number of identities using a training set of images annotated with labels belonging to a disjoint set of identities. Our hierarchical GNN uses a novel approach to merge connected components predicted at each level of the hierarchy to form a new graph at the next level. Unlike fully unsupervised hierarchical clustering, the choice of grouping and complexity criteria stems naturally from supervision in the training set. The resulting method, Hi-LANDER, achieves an average of 49% improvement in F-score and 7% increase in Normalized Mutual Information (NMI) relative to current GNN-based clustering algorithms. Additionally, state-of-the-art GNN-based methods rely on separate models to predict linkage probabilities and node densities as intermediate steps of the clustering process. In contrast, our unified framework achieves a three-fold decrease in computational cost. Our training and inference code are released1.

We propose a new method to detect deepfake images using the cue of the source feature inconsistency within the forged images. It is based on the hypothesis that images’ distinct source features can be preserved and extracted after going through state-of-the-art deepfake generation processes. We introduce a novel representation learning approach, called pair-wise self-consistency learning (PCL), for training ConvNets to extract these source features and detect deepfake images. It is accompanied by a new image synthesis approach, called inconsistency image genera-tor (I2G), to provide richly annotated training data for PCL. Experimental results on seven popular datasets show that our models improve averaged AUC over the state of the art from 96.45% to 98.05% in the in-dataset evaluation and from 86.03% to 92.18% in the cross-dataset evaluation.

We present Long Short-term TRansformer (LSTR), a temporal modeling algorithm for online action detection, which employs a long- and short-term memory mechanism to model prolonged sequence data. It consists of an LSTR encoder that dynamically leverages coarse-scale historical information from an extended temporal window (e.g., 2048 frames spanning of up to 8 minutes), together with an LSTR decoder that focuses on a short time window (e.g., 32 frames spanning 8 seconds) to model the fine-scale characteristics of the data. Compared to prior work, LSTR provides an effective and efficient method to model long videos with fewer heuristics, which is validated by extensive empirical analysis. LSTR achieves state-of-the-art performance on three standard online action detection benchmarks, THUMOS'14, TVSeries, and HACS Segment. Code has been made available at: https://xumingze0308.github.io/projects/lstr.

We propose a way to learn visual features that are compatible with previously computed ones even when they have different dimensions and are learned via different neural network architectures and loss functions. Compatible means that, if such features are used to compare images, then ``new'' features can be compared directly to ``old'' features, so they can be used interchangeably. This enables visual search systems to bypass computing new features for all previously seen images when updating the embedding models, a process known as backfilling. Backward compatibility is critical to quickly deploy new embedding models that leverage ever-growing large-scale training datasets and improvements in deep learning architectures and training methods. We propose a framework to train embedding models, called backward-compatible training (BCT), as a first step towards backward compatible representation learning. In experiments on learning embeddings for face recognition, models trained with BCT successfully achieve backward compatibility without sacrificing accuracy, thus enabling backfill-free model updates of visual embeddings.

Action recognition has seen a dramatic performance improvement in the last few years. Most of the current state-of-the-art literature either aims at improving performance through changes to the backbone CNN network, or exploring different trade-offs between computational efficiency and performance, again through altering the backbone network. However, almost all of these works maintain the same last layers of the network, which simply consist of a global average pooling followed by a fully connected layer. In this work we focus on how to improve the representation capacity of the network, but rather than altering the backbone, we focus on improving the last layers of the network, where changes have low impact in terms of computational cost. In particular, we hypothesize that current architectures have poor sensitivity to finer details and we exploit recent advances in the fine-grained recognition literature to improve our model in this aspect. With the proposed approach, we obtain state-of-the-art performance on Kinetics-400 and Something-Something-V1, the two major large-scale action recognition benchmarks.

In this work, we aim to generate long actions represented as sequences of skeletons. The generated sequences must demonstrate continuous, meaningful human actions, while maintaining coherence among body parts. Instead of generating skeletons sequentially following an autoregressive model, we propose a framework that generates the entire sequence altogether by transforming from a sequence of latent vectors sampled from a Gaussian process (GP). This framework, named Convolutional Sequence Generation Network (CSGN), jointly models structures in temporal and spatial dimensions. It captures the temporal structure at multiple scales through the GP prior and the temporal convolutions; and establishes the spatial connection between the latent vectors and the skeleton graphs via a novel graph refining scheme. It is noteworthy that CSGN allows bidirectional transforms between the latent and the observed spaces, thus enabling semantic manipulation of the action sequences in various forms. We conducted empirical studies on multiple datasets, including a set of high-quality dancing sequences collected by us. The results show that our framework can produce long action sequences that are coherent across time steps and among body parts.

We present a general and flexible video-level framework for learning action models in videos. This method, called temporal segment network (TSN), aims to model long-range temporal structure with a new segment-based sampling and aggregation scheme. This unique design enables the TSN framework to efficiently learn action models by using the whole video. The learned models could be easily deployed for action recognition in both trimmed and untrimmed videos with simple average pooling and multi-scale temporal window integration, respectively. We also study a series of good practices for the implementation of the TSN framework given limited training samples. Our approach obtains the state-the-of-art performance on five challenging action recognition benchmarks: HMDB51 (71.0 percent), UCF101 (94.9 percent), THUMOS14 (80.1 percent), ActivityNet v1.2 (89.6 percent), and Kinetics400 (75.7 percent). In addition, using the proposed RGB difference as a simple motion representation, our method can still achieve competitive accuracy on UCF101 (91.0 percent) while running at 340 FPS. Furthermore, based on the proposed TSN framework, we won the video classification track at the ActivityNet challenge 2016 among 24 teams.

Dynamics of human body skeletons convey significant information for human action recognition. Conventional approaches for modeling skeletons usually rely on hand-crafted parts or traversal rules, thus resulting in limited expressive power and difficulties of generalization. In this work, we propose a novel model of dynamic skeletons called Spatial-Temporal Graph Convolutional Networks (ST-GCN), which moves beyond the limitations of previous methods by automatically learning both the spatial and temporal patterns from data. This formulation not only leads to greater expressive power but also stronger generalization capability. On two large datasets, Kinetics and NTU-RGBD, it achieves substantial improvements over mainstream methods.

High-performance object detection relies on expensive convolutional networks to compute features, often leading to significant challenges in applications, e.g. those that require detecting objects from video streams in real time. The key to this problem is to trade accuracy for efficiency in an effective way, i.e. reducing the computing cost while maintaining competitive performance. To seek a good balance, previous efforts usually focus on optimizing the model architectures. This paper explores an alternative approach, that is, to reallocate the computation over a scale-time space. The basic idea is to perform expensive detection sparsely and propagate the results across both scales and time with substantially cheaper networks, by exploiting the strong correlations among them. Specifically, we present a unified framework that integrates detection, temporal propagation, and across-scale refinement on a Scale-Time Lattice. On this framework, one can explore various strategies to balance performance and cost. Taking advantage of this flexibility, we further develop an adaptive scheme with the detector invoked on demand and thus obtain improved tradeoff. On ImageNet VID dataset, the proposed method can achieve a competitive mAP 79.6% at 20 fps, or 79.0% at 62 fps as a performance/speed tradeoff.1

Neural net classifiers trained on data with annotated class labels can also capture apparent visual similarity among categories without being directed to do so. We study whether this observation can be extended beyond the conventional domain of supervised learning: Can we learn a good feature representation that captures apparent similarity among instances, instead of classes, by merely asking the feature to be discriminative of individual instances? We formulate this intuition as a non-parametric classification problem at the instance-level, and use noise-contrastive estimation to tackle the computational challenges imposed by the large number of instance classes. Our experimental results demonstrate that, under unsupervised learning settings, our method surpasses the state-of-the-art on ImageNet classification by a large margin. Our method is also remarkable for consistently improving test performance with more training data and better network architectures. By fine-tuning the learned feature, we further obtain competitive results for semi-supervised learning and object detection tasks. Our non-parametric model is highly compact: With 128 features per image, our method requires only 600MB storage for a million images, enabling fast nearest neighbour retrieval at the run time.

Despite the remarkable progress in action recognition over the past several years, existing methods remain limited in efficiency and effectiveness. The methods treating appearance and motion as separate streams are usually subject to the cost of optical flow computation, while those relying on 3D convolution on the original video frames often yield inferior performance in practice. In this paper, we propose a new ConvNet architecture for video representation learning, which can derive disentangled components of dynamics purely from raw video frames, without the need of optical flow estimation. Particularly, the learned representation comprises three components for representing static appearance, apparent motion, and appearance changes. We introduce 3D pooling, cost volume processing, and warped feature differences, respectively for extracting the three components above. These modules are incorporated as three branches in our unified network, which share the underlying features and are learned jointly in an end-to-end manner. On two large datasets, UCF101 [22] and Kinetics [16], our method obtained competitive performances with high efficiency, using only the RGB frame sequence as input.

How to leverage the temporal dimension is a key question in video analysis. Recent works suggest an efficient approach to video feature learning, i.e., factorizing 3D convolutions into separate components respectively for spatial and temporal convolutions. The temporal convolution, however, comes with an implicit assumption – the feature maps across time steps are well aligned so that the features at the same locations can be aggregated. This assumption may be overly strong in practical applications, especially in action recognition where the motion serves as a crucial cue. In this work, we propose a new CNN architecture TrajectoryNet, which incorporates trajectory convolution, a new operation for integrating features along the temporal dimension, to replace the existing temporal convolution. This operation explicitly takes into account the changes in contents caused by deformation or motion, allowing the visual features to be aggregated along the the motion paths, trajectories. On two large-scale action recognition datasets, namely, Something-Something and Kinetics, the proposed network architecture achieves notable improvement over strong baselines.

Current action recognition methods heavily rely on trimmed videos for model training. However, it is expensive and time-consuming to acquire a large-scale trimmed video dataset. This paper presents a new weakly supervised architecture, called UntrimmedNet, which is able to directly learn action recognition models from untrimmed videos without the requirement of temporal annotations of action instances. Our UntrimmedNet couples two important components, the classification module and the selection module, to learn the action models and reason about the temporal duration of action instances, respectively. These two components are implemented with feed-forward networks, and UntrimmedNet is therefore an end-to-end trainable architecture. We exploit the learned models for action recognition (WSR) and detection (WSD) on the untrimmed video datasets of THUMOS14 and ActivityNet. Although our UntrimmedNet only employs weak supervision, our method achieves performance superior or comparable to that of those strongly supervised approaches on these two datasets.

Detecting actions in untrimmed videos is an important yet challenging task. In this paper, we present the structured segment network (SSN), a novel framework which models the temporal structure of each action instance via a structured temporal pyramid. On top of the pyramid, we further introduce a decomposed discriminative model comprising two classifiers, respectively for classifying actions and determining completeness. This allows the framework to effectively distinguish positive proposals from background or incomplete ones, thus leading to both accurate recognition and localization. These components are integrated into a unified network that can be efficiently trained in an end-to-end fashion. Additionally, a simple yet effective temporal action proposal scheme, dubbed temporal actionness grouping (TAG) is devised to generate high quality action proposals. On two challenging benchmarks, THUMOS14 and ActivityNet, our method remarkably outperforms previous state-of-the-art methods, demonstrating superior accuracy and strong adaptivity in handling actions with various temporal structures.

Convolutional neural networks (CNNs) have made remarkable progress on scene recognition, partially due to these recent large-scale scene datasets, such as the Places and Places2. Scene categories are often defined by multi-level information, including local objects, global layout, and background environment, thus leading to large intra-class variations. In addition, with the increasing number of scene categories, label ambiguity has become another crucial issue in large-scale classification. This paper focuses on large-scale scene recognition and makes two major contributions to tackle these issues. First, we propose a multi-resolution CNN architecture that captures visual content and structure at multiple levels. The multi-resolution CNNs are composed of coarse resolution CNNs and fine resolution CNNs, which are complementary to each other. Second, we design two knowledge guided disambiguation techniques to deal with the problem of label ambiguity: 1) we exploit the knowledge from the confusion matrix computed on validation data to merge ambiguous classes into a super category and 2) we utilize the knowledge of extra networks to produce a soft label for each image. Then, the super categories or soft labels are employed to guide CNN training on the Places2. We conduct extensive experiments on three large-scale image datasets (ImageNet, Places, and Places2), demonstrating the effectiveness of our approach. Furthermore, our method takes part in two major scene recognition challenges, and achieves the second place at the Places2 challenge in ILSVRC 2015, and the first place at the LSUN challenge in CVPR 2016. Finally, we directly test the learned representations on other scene benchmarks, and obtain the new state-of-the-art results on the MIT Indoor67 (86.7%) and SUN397 (72.0%). We release the code and models at https://github.com/wanglimin/MRCNN-Scene-Recognition.

A considerable portion of web images capture events that occur in our personal lives or social activities. In this paper, we aim to develop an effective method for recognizing events from such images. Despite the sheer amount of study on event recognition, most existing methods rely on videos and are not directly applicable to this task. Generally, events are complex phenomena that involve interactions among people and objects, and therefore analysis of event photos requires techniques that can go beyond recognizing individual objects and carry out joint reasoning based on evidences of multiple aspects. Inspired by the recent success of deep learning, we formulate a multi-layer framework to tackle this problem, which takes into account both visual appearance and the interactions among humans and objects, and combines them via semantic fusion. An important issue arising here is that humans and objects discovered by detectors are in the form of bounding boxes, and there is no straightforward way to represent their interactions and incorporate them with a deep network. We address this using a novel strategy that projects the detected instances onto multi-scale spatial maps. On a large dataset with 60, 000 images, the proposed method achieved substantial improvement over the state-of-the-art, raising the accuracy of event recognition by over 10%.

The archetype hull model is playing an important role in large-scale data analytics and mining, but rarely applied to vision problems. In this paper, we migrate such a geometric model to address face recognition and verification together through proposing a unified archetype hull ranking framework. Upon a scalable graph characterized by a compact set of archetype exemplars whose convex hull encompasses most of the training images, the proposed framework explicitly captures the relevance between any query and the stored archetypes, yielding a rank vector over the archetype hull. The archetype hull ranking is then executed for every block of face images to generate a block wise similarity measure that is achieved by comparing two different rank vectors with respect to the same archetype hull. After integrating block wise similarity measurements with learned importance weights, we accomplish a sensible face similarity measure which can support robust and effective face recognition and verification. We evaluate the face similarity measure in terms of experiments performed on three benchmark face databases Multi-PIE, Pubfig83, and LFW, demonstrating its performance superior to the state-of-the-arts.