We introduce HuTuMotion, an innovative approach for generating natural human motions that navigates latent motion diffusion models by leveraging few-shot human feedback. Unlike existing approaches that sample latent variables from a standard normal prior distribution, our method adapts the prior distribution to better suit the characteristics of the data, as indicated by human feedback, thus enhancing the quality of motion generation. Furthermore, our findings reveal that utilizing few-shot feedback can yield performance levels on par with those attained through extensive human feedback. This discovery emphasizes the potential and efficiency of incorporating few-shot human-guided optimization within latent diffusion models for personalized and style-aware human motion generation applications. The experimental results show the significantly superior performance of our method over existing state-of-the-art approaches.
论文检索
输入标题、作者或关键词，从 2,866 篇学术成果中精准定位
Human motion generation aims to produce plausible human motion sequences according to various conditional inputs, such as text or audio. Despite the feasibility of existing methods in generating motion based on short prompts and simple motion patterns, they encounter difficulties when dealing with long prompts or complex motions. The challenges are two-fold: 1) the scarcity of human motion-captured data for long prompts and complex motions. 2) the high diversity of human motions in the temporal domain and the substantial divergence of distributions from conditional modalities, leading to a many-to-many mapping problem when generating motion with complex and long texts. In this work, we address these gaps by 1) elaborating the first dataset pairing long textual descriptions and 3D complex motions (HumanLong3D), and 2) proposing an autoregressive motion diffusion model (AMD). Specifically, AMD integrates the text prompt at the current timestep with the text prompt and action sequences at the previous timestep as conditional information to predict the current action sequences in an iterative manner. Furthermore, we present its generalization for X-to-Motion with “No Modality Left Behind”, enabling for the first time the generation of high-definition and high-fidelity human motions based on user-defined modality input.
Traditional Radiance Field (RF) representations capture details of a specific scene and must be trained afresh on each scene. Semantic feature fields have been added to RFs to facilitate several segmentation tasks. Generalised RF representations learn the principles of view interpolation. A generalised RF can render new views of an unknown and untrained scene, given a few views. We present a way to distil feature fields into the generalised GNT representation. Our GSN representation generates new views of unseen scenes on the fly along with consistent, per-pixel semantic features. This enables multi-view segmentation of arbitrary new scenes. We show different semantic features being distilled into generalised RFs. Our multi-view segmentation results are on par with methods that use traditional RFs. GSN closes the gap between standard and generalisable RF methods significantly. Project Page: https://vinayak-vg.github.io/GSN/
Convolutional Neural Networks (CNNs) have exhibited great performance in discriminative feature learning for complex visual tasks. Besides discrimination power, interpretability is another important yet under-explored property for CNNs. One difficulty in the CNN interpretability is that filters and image classes are entangled. In this paper, we introduce a novel pathway to alleviate the entanglement between filters and image classes. The proposed pathway groups the filters in a late conv-layer of CNN into class-specific clusters. Clusters and classes are in a one-to-one relationship. Specifically, we use the Bernoulli sampling to generate the filter-cluster assignment matrix from a learnable filter-class correspondence matrix. To enable end-to-end optimization, we develop a novel reparameterization trick for handling the non-differentiable Bernoulli sampling. We evaluate the effectiveness of our method on ten widely used network architectures (including nine CNNs and a ViT) and five benchmark datasets. Experimental results have demonstrated that our method PICNN (the combination of standard CNNs with our proposed pathway) exhibits greater interpretability than standard CNNs while achieving higher or comparable discrimination power.
Recent advancement in computer vision has significantly lowered the barriers to artistic creation. Exemplar-based image translation methods have attracted much attention due to flexibility and controllability. However, these methods hold assumptions regarding semantics or require semantic information as the input, while accurate semantics is not easy to obtain in artistic images. Besides, these methods suffer from cross-domain artifacts due to training data prior and generate imprecise structure due to feature compression in the spatial domain. In this paper, we propose an arbitrary Style Image Manipulation Network (SIM-Net), which leverages semantic-free information as guidance and a region transportation strategy in a self-supervised manner for image generation. Our method balances computational efficiency and high resolution to a certain extent. Moreover, our method facilitates zero-shot style image manipulation. Both qualitative and quantitative experiments demonstrate the superiority of our method over state-of-the-art methods.Code is available at https://github.com/SnailForce/SIM-Net.
Improving Panoptic Narrative Grounding by Harnessing Semantic Relationships and Visual Confirmation
PDF ↗Recent advancements in single-stage Panoptic Narrative Grounding (PNG) have demonstrated significant potential. These methods predict pixel-level masks by directly matching pixels and phrases. However, they often neglect the modeling of semantic and visual relationships between phrase-level instances, limiting their ability for complex multi-modal reasoning in PNG. To tackle this issue, we propose XPNG, a “differentiation-refinement-localization” reasoning paradigm for accurately locating instances or regions. In XPNG, we introduce a Semantic Context Convolution (SCC) module to leverage semantic priors for generating distinctive features. This well-crafted module employs a combination of dynamic channel-wise convolution and pixel-wise convolution to embed semantic information and establish inter-object relationships guided by semantics. Subsequently, we propose a Visual Context Verification (VCV) module to provide visual cues, eliminating potential space biases introduced by semantics and further refining the visual features generated by the previous module. Extensive experiments on PNG benchmark datasets reveal that our approach achieves state-of-the-art performance, significantly outperforming existing methods by a considerable margin and yielding a 3.9-point improvement in overall metrics. Our codes and results are available at our project webpage: https://github.com/TianyuGoGO/XPNG.
Novel-view synthesis with sparse input views is important for real-world applications like AR/VR and autonomous driving. Recent methods have integrated depth information into NeRFs for sparse input synthesis, leveraging depth prior for geometric and spatial understanding. However, most existing works tend to overlook inaccuracies within depth maps and have low time efficiency. To address these issues, we propose a depth-guided robust and fast point cloud fusion NeRF for sparse inputs. We perceive radiance fields as an explicit voxel grid of features. A point cloud is constructed for each input view, characterized within the voxel grid using matrices and vectors. We accumulate the point cloud of each input view to construct the fused point cloud of the entire scene. Each voxel determines its density and appearance by referring to the point cloud of the entire scene. Through point cloud fusion and voxel grid fine-tuning, inaccuracies in depth values are refined or substituted by those from other views. Moreover, our method can achieve faster reconstruction and greater compactness through effective vector-matrix decomposition. Experimental results underline the superior performance and time efficiency of our approach compared to state-of-the-art baselines.
Most of existing correspondence pruning methods only concentrate on gathering the context information as much as possible while neglecting effective ways to utilize such information. In order to tackle this dilemma, in this paper we propose Graph Context Transformation Network (GCT-Net) enhancing context information to conduct consensus guidance for progressive correspondence pruning. Specifically, we design the Graph Context Enhance Transformer which first generates the graph network and then transforms it into multi-branch graph contexts. Moreover, it employs self-attention and cross-attention to magnify characteristics of each graph context for emphasizing the unique as well as shared essential information. To further apply the recalibrated graph contexts to the global domain, we propose the Graph Context Guidance Transformer. This module adopts a confident-based sampling strategy to temporarily screen high-confidence vertices for guiding accurate classification by searching global consensus between screened vertices and remaining ones. The extensive experimental results on outlier removal and relative pose estimation clearly demonstrate the superior performance of GCT-Net compared to state-of-the-art methods across outdoor and indoor datasets.
Self-Supervised Learning (SSL) methods harness the concept of semantic invariance by utilizing data augmentation strategies to produce similar representations for different deformations of the same input. Essentially, the model captures the shared information among multiple augmented views of samples, while disregarding the non-shared information that may be beneficial for downstream tasks. To address this issue, we introduce a module called CompMod with Meta Comprehensive Regularization (MCR), embedded into existing self-supervised frameworks, to make the learned representations more comprehensive. Specifically, we update our proposed model through a bi-level optimization mechanism, enabling it to capture comprehensive features. Additionally, guided by the constrained extraction of features using maximum entropy coding, the self-supervised learning model learns more comprehensive features on top of learning consistent features. In addition, we provide theoretical support for our proposed method from information theory and causal counterfactual perspective. Experimental results show that our method achieves significant improvement in classification, object detection and semantic segmentation tasks on multiple benchmark datasets.
Although neural models have achieved remarkable performance, they still encounter doubts due to the intransparency. To this end, model prediction explanation is attracting more and more attentions. However, current methods rarely incorporate external knowledge and still suffer from three limitations: (1) Neglecting concept completeness. Merely selecting concepts may not sufficient for prediction. (2) Lacking concept fusion. Failure to merge semantically-equivalent concepts. (3) Difficult in manipulating model behavior. Lack of verification for explanation on original model. To address these issues, we propose a novel knowledge-aware neuron interpretation framework to explain model predictions for image scene classification. Specifically, for concept completeness, we present core concepts of a scene based on knowledge graph, ConceptNet, to gauge the completeness of concepts. Our method, incorporating complete concepts, effectively provides better prediction explanations compared to baselines. Furthermore, for concept fusion, we introduce a knowledge graph-based method known as Concept Filtering, which produces over 23% point gain on neuron behaviors for neuron interpretation. At last, we propose Model Manipulation, which aims to study whether the core concepts based on ConceptNet could be employed to manipulate model behavior. The results show that core concepts can effectively improve the performance of original model by over 26%.
Salient Object Ranking (SOR) is the process of predicting the order of an observer's attention to objects when viewing a complex scene. Existing SOR methods primarily focus on ranking various scene objects simultaneously by exploring their spatial and semantic properties. However, their solutions of simultaneously ranking all salient objects do not align with human viewing behavior, and may result in incorrect attention shift predictions. We observe that humans view a scene through a sequential and continuous process involving a cycle of foveating to objects of interest with our foveal vision while using peripheral vision to prepare for the next fixation location. For instance, when we see a flying kite, our foveal vision captures the kite itself, while our peripheral vision can help us locate the person controlling it such that we can smoothly divert our attention to it next. By repeatedly carrying out this cycle, we can gain a thorough understanding of the entire scene. Based on this observation, we propose to model the dynamic interplay between foveal and peripheral vision to predict human attention shifts sequentially. To this end, we propose a novel SOR model, SeqRank, which reproduces foveal vision to extract high-acuity visual features for accurate salient instance segmentation while also modeling peripheral vision to select the object that is likely to grab the viewer’s attention next. By incorporating both types of vision, our model can mimic human viewing behavior better and provide a more faithful ranking among various scene objects. Most notably, our model improves the SA-SOR/MAE scores by +6.1%/-13.0% on IRSR, compared with the state-of-the-art. Extensive experiments show the superior performance of our model on the SOR benchmarks. Code is available at https://github.com/guanhuankang/SeqRank.
Large Vision-Language Models (LVLMs) such as MiniGPT-4 and LLaVA have demonstrated the capability of understanding images and achieved remarkable performance in various visual tasks. Despite their strong abilities in recognizing common objects due to extensive training datasets, they lack specific domain knowledge and have a weaker understanding of localized details within objects, which hinders their effectiveness in the Industrial Anomaly Detection (IAD) task. On the other hand, most existing IAD methods only provide anomaly scores and necessitate the manual setting of thresholds to distinguish between normal and abnormal samples, which restricts their practical implementation. In this paper, we explore the utilization of LVLM to address the IAD problem and propose AnomalyGPT, a novel IAD approach based on LVLM. We generate training data by simulating anomalous images and producing corresponding textual descriptions for each image. We also employ an image decoder to provide fine-grained semantic and design a prompt learner to fine-tune the LVLM using prompt embeddings. Our AnomalyGPT eliminates the need for manual threshold adjustments, thus directly assesses the presence and locations of anomalies. Additionally, AnomalyGPT supports multi-turn dialogues and exhibits impressive few-shot in-context learning capabilities. With only one normal shot, AnomalyGPT achieves the state-of-the-art performance with an accuracy of 86.1%, an image-level AUC of 94.1%, and a pixel-level AUC of 95.3% on the MVTec-AD dataset.
Among various interactions between humans, such as eye contact and gestures, physical interactions by contact can act as an essential moment in understanding human behaviors. Inspired by this fact, given a 3D partner human with the desired interaction label, we introduce a new task of 3D human generation in terms of physical contact. Unlike previous works of interacting with static objects or scenes, a given partner human can have diverse poses and different contact regions according to the type of interaction. To handle this challenge, we propose a novel method of generating interactive 3D humans for a given partner human based on a guided diffusion framework (ContactGen in short). Specifically, we newly present a contact prediction module that adaptively estimates potential contact regions between two input humans according to the interaction label. Using the estimated potential contact regions as complementary guidances, we dynamically enforce ContactGen to generate interactive 3D humans for a given partner human within a guided diffusion model. We demonstrate ContactGen on the CHI3D dataset, where our method generates physically plausible and diverse poses compared to comparison methods.
SDAC: A Multimodal Synthetic Dataset for Anomaly and Corner Case Detection in Autonomous Driving
PDF ↗Nowadays, closed-set perception methods for autonomous driving perform well on datasets containing normal scenes. However, they still struggle to handle anomalies in the real world, such as unknown objects that have never been seen while training. The lack of public datasets to evaluate the model performance on anomaly and corner cases has hindered the development of reliable autonomous driving systems. Therefore, we propose a multimodal Synthetic Dataset for Anomaly and Corner case detection, called SDAC, which encompasses anomalies captured from multi-view cameras and the LiDAR sensor, providing a rich set of annotations for multiple mainstream perception tasks. SDAC is the first public dataset for autonomous driving that categorizes anomalies into object, scene, and scenario levels, allowing the evaluation under different anomalous conditions. Experiments show that closed-set models suffer significant performance drops on anomaly subsets in SDAC. Existing anomaly detection methods fail to achieve satisfactory performance, suggesting that anomaly detection remains a challenging problem. We anticipate that our SDAC dataset could foster the development of safe and reliable systems for autonomous driving.
This paper proposes an end-to-end framework for generating 3D human pose datasets using Neural Radiance Fields (NeRF). Public datasets generally have limited diversity in terms of human poses and camera viewpoints, largely due to the resource-intensive nature of collecting 3D human pose data. As a result, pose estimators trained on public datasets significantly underperform when applied to unseen out-of-distribution samples. Previous works proposed augmenting public datasets by generating 2D-3D pose pairs or rendering a large amount of random data. Such approaches either overlook image rendering or result in suboptimal datasets for pre-trained models. Here we propose PoseGen, which learns to generate a dataset (human 3D poses and images) with a feedback loss from a given pre-trained pose estimator. In contrast to prior art, our generated data is optimized to improve the robustness of the pre-trained model. The objective of PoseGen is to learn a distribution of data that maximizes the prediction error of a given pre-trained model. As the learned data distribution contains OOD samples of the pre-trained model, sampling data from such a distribution for further fine-tuning a pre-trained model improves the generalizability of the model. This is the first work that proposes NeRFs for 3D human data generation. NeRFs are data-driven and do not require 3D scans of humans. Therefore, using NeRF for data generation is a new direction for convenient user-specific data generation. Our extensive experiments show that the proposed PoseGen improves two baseline models (SPIN and HybrIK) on four datasets with an average 6% relative improvement.
Learning Multi-Scale Video-Text Correspondence for Weakly Supervised Temporal Article Gronding
PDF ↗Weakly Supervised temporal Article Grounding (WSAG) is a challenging and practical task in video understanding. Specifically, given a video and a relevant article, whose sentences are at different semantic scales, WSAG aims to localize corresponding video segments for all “groundable” sentences. Compared to other grounding tasks, e.g., localizing one target segment with respect to a given sentence query, WSAG confronts an essential obstacle rooted in the intricate multi-scale information inherent within both textual and visual modalities. Existing methods overlook the modeling and alignment of such structured information present in multi-scale video segments and hierarchical textual content. To this end, we propose a Multi-Scale Video-Text Correspondence Learning (MVTCL) framework, which enhances the grounding performance in complex scenes by modeling multi-scale semantic correspondence both within and between modalities. Specifically, MVTCL initially aggregates video content spanning distinct temporal scales and leverages hierarchical textual relationships in both temporal and semantic dimensions via a semantic calibration module. Then multi-scale contrastive learning module is introduced to generate more discriminative representations by selecting typical contexts and performing inter-video contrastive learning. Through the multi-scale semantic calibration architecture and supervision design, our method achieves new state-of-the-art performance on existing WSAG benchmarks.
One of the ultimate goals of representation learning is to achieve compactness within a class and well-separability between classes. Many outstanding metric-based and prototype-based methods following the Expectation-Maximization paradigm, have been proposed for this objective. However, they inevitably introduce biases into the learning process, particularly with long-tail distributed training data. In this paper, we reveal that the class prototype is not necessarily to be derived from training features and propose a novel perspective to use pre-defined class anchors serving as feature centroid to unidirectionally guide feature learning. However, the pre-defined anchors may have a large semantic distance from the pixel features, which prevents them from being directly applied. To address this issue and generate feature centroid independent from feature learning, a simple yet effective Semantic Anchor Regularization (SAR) is proposed. SAR ensures the inter-class separability of semantic anchors in the semantic space by employing a classifier-aware auxiliary cross-entropy loss during training via disentanglement learning. By pulling the learned features to these semantic anchors, several advantages can be attained: 1) the intra-class compactness and naturally inter-class separability, 2) induced bias or errors from feature learning can be avoided, and 3) robustness to the long-tailed problem. The proposed SAR can be used in a plug-and-play manner in the existing models. Extensive experiments demonstrate that the SAR performs better than previous sophisticated prototype-based methods. The implementation is available at https://github.com/geyanqi/SAR.
Convolutional neural networks-based video de-raining methods commonly rely on dense intensity frames captured by CMOS sensors. However, the limited temporal resolution of these sensors hinders the capture of dynamic rainfall information, limiting further improvement in de-raining performance. This study aims to overcome this issue by incorporating the neuromorphic event signal into the video de-raining to enhance the dynamic information perception. Specifically, we first utilize the dynamic information from the event signal as prior knowledge, and integrate it into existing de-raining objectives to better constrain the solution space. We then design an optimization algorithm to solve the objective, and construct a de-raining network with CNNs as the backbone architecture using a modular strategy to mimic the optimization process. To further explore the temporal correlation of the event signal, we incorporate a spiking self-attention module into our network. By leveraging the low latency and high temporal resolution of the event signal, along with the spatial and temporal representation capabilities of convolutional and spiking neural networks, our model captures more accurate dynamic information and significantly improves de-raining performance. For example, our network achieves a 1.24dB improvement on the SynHeavy25 dataset compared to the previous state-of-the-art method, while utilizing only 39% of the parameters.
Composite Sketch+Text Queries for Retrieving Objects with Elusive Names and Complex Interactions
PDF ↗Non-native speakers with limited vocabulary often struggle to name specific objects despite being able to visualize them, e.g., people outside Australia searching for ‘numbats.’ Further, users may want to search for such elusive objects with difficult-to-sketch interactions, e.g., “numbat digging in the ground.” In such common but complex situations, users desire a search interface that accepts composite multimodal queries comprising hand-drawn sketches of “difficult-to-name but easy-to-draw” objects and text describing “difficult-to-sketch but easy-to-verbalize” object's attributes or interaction with the scene. This novel problem statement distinctly differs from the previously well-researched TBIR (text-based image retrieval) and SBIR (sketch-based image retrieval) problems. To study this under-explored task, we curate a dataset, CSTBIR (Composite Sketch+Text Based Image Retrieval), consisting of ~2M queries and 108K natural scene images. Further, as a solution to this problem, we propose a pretrained multimodal transformer-based baseline, STNet (Sketch+Text Network), that uses a hand-drawn sketch to localize relevant objects in the natural scene image, and encodes the text and image to perform image retrieval. In addition to contrastive learning, we propose multiple training objectives that improve the performance of our model. Extensive experiments show that our proposed method outperforms several state-of-the-art retrieval methods for text-only, sketch-only, and composite query modalities. We make the dataset and code available at: https://vl2g.github.io/projects/cstbir.
During the preceding biennium, vision-language pre-training has achieved noteworthy success on several downstream tasks. Nevertheless, acquiring high-quality image-text pairs, where the pairs are entirely exclusive of each other, remains a challenging task, and noise exists in the commonly used datasets. To address this issue, we propose SoftCLIP, a novel approach that relaxes the strict one-to-one constraint and achieves a soft cross-modal alignment by introducing a softened target, which is generated from the fine-grained intra-modal self-similarity. The intra-modal guidance is indicative to enable two pairs have some local similarities and model many-to-many relationships between the two modalities. Besides, since the positive still dominates in the softened target distribution, we disentangle the negatives in the distribution to further boost the relation alignment with the negatives in the cross-modal learning. Extensive experiments demonstrate the effectiveness of SoftCLIP. In particular, on ImageNet zero-shot classification task, using CC3M/CC12M as pre-training dataset, SoftCLIP brings a top-1 accuracy improvement of 6.8%/7.2% over the CLIP baseline.